icml_2017.json

[{"When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\\ell_2$-consistency and Neuroscience Applications": ["Hao Zhou", "Yilin Zhang", "Vamsi Ithapu", "Sterling Johnson", "Grace Wahba", "Vikas Singh"], "ChoiceRank: Identifying Preferences from Node Traffic in Networks": ["Lucas Maystre", "Matthias Grossglauser"], "iSurvive: An Interpretable, Event-time Prediction Model for mHealth": ["Walter Dempsey", "Alexander Moreno", "James Rehg", "Susan Murphy", "Chris Scott", "Michael Dennis", "David Gustafson"], "Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space": ["Jose Hernandez-Lobato", "James Requeima", "Edward Pyzer-Knapp", "alan Aspuru-Guzik"], "A Closer Look at Memorization in Deep Networks": ["David Krueger", "Yoshua Bengio", "Stanislaw Jastrzebsk", "Maxinder S. Kanwal", "Nicolas Ballas", "Asja Fischer", "Emmanuel Bengio", "Devansh Arpit", "Tegan Maharaj", "Aaron Courville", "Simon Lacoste-Julien"], "Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data": ["Xixian Chen", "Michael Lyu", "Irwin King"], "Approximate Steepest Coordinate Descent": ["Sebastian Stich", "Anant Raj", "Martin Jaggi"], "The Shattered Gradients Problem: If resnets are the answer, then what is the question?": ["David Balduzzi", "Marcus Frean", "Wan-Duo Ma", "Brian McWilliams", "Lennox Leary", "John Lewis"], "Recovery Guarantees for One-hidden-layer Neural Networks": ["Kai Zhong", "Zhao Song", "Prateek Jain", "Peter Bartlett", "Inderjit Dhillon"], "Reduced Space and Faster Convergence in Imperfect-Information Games via Pruning": ["Noam Brown", "Tuomas Sandholm"], "MEC: Memory-efficient Convolution for Deep Neural Network": ["Minsik Cho", "Daniel Brand"], "A Birth-Death Process for Feature Allocation": ["Konstantina Palla", "David Knowles", "Zoubin Ghahramani"], "Pain-Free Random Differential Privacy with Sensitivity Sampling": ["Benjamin Rubinstein", "Francesco Ald\u00e0"], "Programming with a Differentiable Forth Interpreter": ["Matko Bo\u0161njak", "Tim Rockt\u00e4schel", "Jason Naradowsky", "Sebastian Riedel"], "Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution": ["Po-Wei Chou", "Daniel Maturana", "Sebastian Scherer"], "Robust Guarantees of Stochastic Greedy Algorithms": ["Yaron Singer", "Avinatan Hassidim"], "Sequence Modeling via Segmentations": ["Chong Wang", "Yining Wang", "Po-Sen Huang", "Abdelrahman Mohammad", "Dengyong Zhou", "Li Deng"], "Bayesian inference on random simple graphs with power law degree distributions": ["Juho Lee", "Creighton Heaukulani", "Zoubin Ghahramani", "Lancelot F. James", "Seungjin Choi"], "Tensor Balancing on Statistical Manifold": ["Mahito Sugiyama", "Hiroyuki Nakahara", "Koji Tsuda"], "Generalization and Equilibrium in Generative Adversarial Nets (GANs)": ["Sanjeev Arora", "Rong Ge", "Yingyu Liang", "Tengyu Ma", "Yi Zhang"], "The Sample Complexity of Online One-Class Collaborative Filtering": ["Reinhard Heckel", "Kannan Ramchandran"], "Gradient Coding: Avoiding Stragglers in Distributed Learning": ["Rashish Tandon", "Qi Lei", "Alexandros Dimakis", "NIKOS KARAMPATZIAKIS"], "Connected Subgraph Detection with Mirror Descent on SDPs": ["Cem Aksoylar", "Orecchia Lorenzo", "Venkatesh Saligrama"], "Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC": ["Yulai Cong", "Bo Chen", "Hongwei Liu", "Mingyuan Zhou"], "Regret Minimization in Behaviorally-Constrained Zero-Sum Games": ["Gabriele Farina", "Christian Kroer", "Tuomas Sandholm"], "Asynchronous Distributed Variational Gaussian Processes for Regression": ["Hao Peng", "Shandian Zhe", "Xiao Zhang", "Yuan Qi"], "Random Feature Expansions for Deep Gaussian Processes": ["Kurt Cutajar", "Edwin Bonilla", "Pietro Michiardi", "Maurizio Filippone"], "Leveraging Node Attributes for Incomplete Relational Data": ["He Zhao", "Lan Du", "Wray Buntine"], "Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference": ["Aditya Chaudhry", "Pan Xu", "Quanquan Gu"], "Evaluating the Variance of Likelihood-Ratio Gradient Estimators": ["Seiya Tokui", "Issei Sato"], "Efficient Regret Minimization in Non-Convex Games": ["Elad Hazan", "Karan Singh", "Cyril Zhang"], "Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU": ["Zeyuan Allen-Zhu", "Yuanzhi Li"], "Canopy --- Fast Sampling with Cover Trees": ["Manzil Zaheer", "Satwik Kottur", "Amr Ahmed", "Jose Moura", "Alex Smola"], "Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation": ["Yacine Jernite", "Anna Choromanska", "David Sontag"], "Robust Submodular Maximization: A Non-Uniform Partitioning Approach": ["Ilija Bogunovic", "Slobodan Mitrovic", "Jonathan Scarlett", "Volkan Cevher"], "Dynamic Word Embeddings": ["Robert Bamler", "Stephan Mandt"], "Robust Adversarial Reinforcement Learning": ["Lerrel Pinto", "James Davidson", "Rahul Sukthankar", "Abhinav Gupta"], "Multi-Class Optimal Margin Distribution Machine": ["Teng Zhang", "Zhi-Hua Zhou"], "Just Sort It! A Simple and Effective Approach to Active Preference Learning": ["Lucas Maystre", "Matthias Grossglauser"], "Zero-Inflated Exponential Family Embeddings": ["Liping Liu", "David Blei"], "Variational Boosting: Iteratively Refining Posterior Approximations": ["Andrew Miller", "Nicholas J Foti", "Ryan Adams"], "Convexified Convolutional Neural Networks": ["Yuchen Zhang", "Percy Liang", "Martin Wainwright"], "Geometry of Neural Network Loss Surfaces via Random Matrix Theory": ["Jeffrey Pennington", "Yasaman Bahri"], "Follow the Moving Leader in Deep Learning": ["Shuai Zheng", "James Kwok"], "Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections": ["zakaria mhammedi", "Andrew Hellicar", "James Bailey", "Ashfaqur Rahman"], "Coupling Distributed and Symbolic Execution for Natural Language Queries": ["Lili Mou", "Zhengdong Lu", "Hang Li", "Zhi Jin"], "Distributed and Provably Good Seedings for k-Means in Constant Rounds": ["Olivier Bachem", "Mario Lucic", "Andreas Krause"], "Learning Hawkes Processes from Short Doubly-Censored Event Sequences": ["Hongteng Xu", "Dixin Luo", "Hongyuan Zha"], "A Laplacian Framework for Option Discovery in Reinforcement Learning": ["Marlos C. Machado", "Marc Bellemare", "Michael Bowling"], "Spherical Structured Feature Maps for Kernel Approximation": ["Yueming LYU"], "Probabilistic Submodular Maximization in Sub-Linear Time": ["Serban A Stan", "Morteza Zadimoghaddam", "Andreas Krause", "Amin Karbasi"], "Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction": ["Wen Sun", "Arun Venkatraman", "Geoff Gordon", "Byron Boots", "Drew Bagnell"], "Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition": ["Zeyuan Allen-Zhu", "Yuanzhi Li"], "Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering": ["Bo Yang", "Xiao Fu", "Nicholas Sidiropoulos", "Mingyi Hong"], "Dueling Bandits with Weak Regret": ["Bangrui Chen", "Peter Frazier"], "Optimal and Adaptive Off-policy Evaluation in Contextual Bandits": ["Yu-Xiang Wang", "Alekh Agarwal", "Miroslav Dudik"], "Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter": ["Zeyuan Allen-Zhu"], "Variants of RMSProp and Adagrad with Logarithmic Regret Bounds": ["Mahesh Chandra Mukkamala", "Matthias Hein"], "Being Robust (in High Dimensions) Can Be Practical": ["Ilias Diakonikolas", "Gautam Kamath", "Daniel Kane", "Jerry Li", "Ankur Moitra", "Alistair Stewart"], "Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things": ["Ashish Kumar", "Saurabh Goyal", "Manik Varma"], "Learned Optimizers that Scale and Generalize": ["Olga Wichrowska", "Niru Maheswaranathan", "Matthew Hoffman", "Sergio G\u00f3mez Colmenarejo", "Misha Denil", "Nando de Freitas", "Jascha Sohl-Dickstein"], "An Infinite Hidden Markov Model With Similarity-Biased Transitions": ["Colin Dawson", "Chaofan Huang", "Clayton T. Morrison"], "Zonotope hit-and-run for efficient sampling from projection DPPs": ["Guillaume Gautier", "R\u00e9mi Bardenet", "Michal Valko"], "DARLA: Improving Zero-Shot Transfer in Reinforcement Learning": ["Irina Higgins", "Arka Pal", "Andrei A Rusu", "Loic Matthey", "Christopher Burgess", "Alexander Pritzel", "Matthew Botvinick", "Charles Blundell", "Alexander Lerchner"], "Online and Linear-Time Attention by Enforcing Monotonic Alignments": ["Colin Raffel", "Thang Luong", "Peter Liu", "Ron Weiss", "Douglas Eck"], "Learning Latent Space Models with Angular Constraints": ["Pengtao Xie", "Yuntian Deng", "Yi Zhou", "Abhimanu Kumar", "Yaoliang Yu", "James Zou", "Eric Xing"], "SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient": ["Lam M Nguyen", "Jie Liu", "Katya Scheinberg", "Martin Takac"], "Beyond Filters: Compact Feature Map for Portable Deep Model": ["Yunhe Wang", "Chang Xu", "Chao Xu", "Dacheng Tao"], "High-Dimensional Structured Quantile Regression": ["Vidyashankar Sivakumar", "Arindam Banerjee"], "Multi-task Learning with Labeled and Unlabeled Tasks": ["Anastasia Pentina", "Christoph Lampert"], "GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization": ["Li Shen", "Wei Liu", "Ganzhao Yuan", "Shiqian Ma"], "Language Modeling with Gated Convolutional Networks": ["Yann Dauphin", "Angela Fan", "Michael Auli", "David Grangier"], "Learning Gradient Descent: Better Generalization and Longer Horizons": ["Kaifeng Lv", "Shunhua Jiang", "Jian Li"], "Sequence to Better Sequence: Continuous Revision of Combinatorial Structures": ["Jonas Mueller", "David Gifford", "Tommi Jaakkola"], "Distributed Batch Gaussian Process Optimization": ["Erik Daxberger", "Bryan Kian Hsiang Low"], "Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data": ["Tomoya Sakai", "Marthinus C du Plessis", "Gang Niu", "Masashi Sugiyama"], "Online Learning to Rank in Stochastic Click Models": ["Masrour Zoghi", "Tomas Tunys", "Mohammad Ghavamzadeh", "Branislav Kveton", "Csaba Szepesvari", "Zheng Wen"], "Exact MAP Inference by Avoiding Fractional Vertices": ["Erik Lindgren", "Alexandros Dimakis", "Adam Klivans"], "Forest-type Regression with General Losses and Robust Forest": ["Hanbo Li", "Andrew Martin"], "Uncorrelation and Evenness: a New Diversity-Promoting Regularizer": ["Pengtao Xie", "Aarti Singh", "Eric Xing"], "Coherent probabilistic forecasts for hierarchical time series": ["Souhaib Ben Taieb", "James Taylor", "Rob Hyndman"], "Evaluating Bayesian Models with Posterior Dispersion Indices": ["Alp Kucukelbir", "Yixin Wang", "David Blei"], "Failures of Gradient-Based Deep Learning": ["Shaked Shammah", "Shai Shalev-Shwartz", "Ohad Shamir"], "Global optimization of Lipschitz functions": ["C\u00e9dric Malherbe", "Nicolas Vayatis"], "Approximate Newton Methods and Their Local Convergence": ["Haishan Ye", "Luo Luo", "Zhihua Zhang"], "An Alternative Softmax Operator for Reinforcement Learning": ["Kavosh Asadi", "Michael L. Littman"], "A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions": ["Jayadev Acharya", "Hirakendu Das", "Alon Orlitsky", "Ananda Suresh"], "Selective Inference for Sparse High-Order Interaction Models": ["Shinya Suzumura", "Kazuya Nakagawa", "Yuta Umezu", "Koji Tsuda", "Ichiro Takeuchi"], "Real-Time Adaptive Image Compression": ["Oren Rippel", "Lubomir Bourdev"], "Robust Gaussian Graphical Model Estimation with Arbitrary Corruption": ["Lingxiao Wang", "Quanquan Gu"], "Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity": ["Eunho Yang", "Aurelie Lozano"], "On the Sampling Problem for Kernel Quadrature": ["Francois-Xavier Briol", "Chris J Oates", "Jon Cockayne", "Wilson Ye Chen", "Mark Girolami"], "Spectral Learning from a Single Trajectory under Finite-State Policies": ["Borja de Balle Pigem", "Odalric Maillard"], "Relative Fisher Information and Natural Gradient for Learning Large Modular Models": ["Ke Sun", "Frank Nielsen"], "Learning Deep Architectures via Generalized Whitened Neural Networks": ["Ping Luo"], "Learning Algorithms for Active Learning": ["Philip Bachman", "Alessandro Sordoni", "Adam Trischler"], "Convex Phase Retrieval without Lifting via PhaseMax": ["Tom Goldstein", "Christoph Studer"], "Sliced Wasserstein Kernel for Persistence Diagrams": ["Mathieu Carri\u00e8re", "Marco Cuturi", "Steve Oudot"], "Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression": ["PENGFEI WEI", "Ramon Sagarna", "Yiping Ke", "Yew Soon ONG", "CHI GOH"], "Device Placement Optimization with Reinforcement Learning": ["Azalia Mirhoseini", "Hieu Pham", "Quoc Le", "benoit steiner", "Mohammad Norouzi", "Rasmus Larsen", "Yuefeng Zhou", "Naveen Kumar", "Samy Bengio", "Jeff Dean"], "Emulating the Expert: Inverse Optimization through Online Learning": ["Sebastian Pokutta", "Andreas B\u00e4rmann", "Oskar Schneider"], "Estimating the unseen from multiple populations": ["Aditi Raghunathan", "Greg Valiant", "James Zou"], "Multilabel Classification with Group Testing and Codes": ["Shashanka Ubaru", "Arya Mazumdar"], "Unsupervised Learning by Predicting Noise": ["Piotr Bojanowski", "Armand Joulin"], "Adapting Kernel Representations Online Using Submodular Maximization": ["Matthew Schlegel", "Yangchen Pan", "Jiecao Chen", "Martha White"], "Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization": ["Bo Liu", "Xiaotong Yuan", "Lezi Wang", "Qingshan Liu", "Dimitris Metaxas"], "AdaNet: Adaptive Structural Learning of Artificial Neural Networks": ["Corinna Cortes", "Xavi Gonzalvo", "Vitaly Kuznetsov", "Mehryar Mohri", "Scott Yang"], "Sub-sampled Cubic Regularization for Non-convex Optimization": ["Jonas Kohler", "Aurelien Lucchi"], "StingyCD: Safely Avoiding Wasteful Updates in Coordinate Descent": ["Tyler Johnson", "Carlos Guestrin"], "Learning in POMDPs with Monte Carlo Tree Search": ["Sammie Katt", "Frans A Oliehoek", "Chris Amato"], "Test of Time Award": [""], "On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit": ["Jie Shen", "Ping Li"], "Active Learning for Top-$K$ Rank Aggregation from Noisy Comparisons": ["Soheil Mohajer", "Changho Suh", "Adel Elmahdy"], "On Approximation Guarantees for Greedy Low Rank Optimization": ["RAJIV KHANNA", "Ethan Elenberg", "Alexandros Dimakis", "Joydeep Ghosh", "Sahand Negahban"], "Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging": ["Shusen Wang", "Alex Gittens", "Michael Mahoney"], "Maximum Selection and Ranking under Noisy Comparisons": ["Moein Falahatgar", "Alon Orlitsky", "Venkatadheeraj Pichapati", "Ananda Suresh"], "Stochastic Variance Reduction Methods for Policy Evaluation": ["Simon Du", "Jianshu Chen", "Lihong Li", "Lin Xiao", "Dengyong Zhou"], "Nonparanormal Information Estimation": ["Shashank Singh", "Barnab\u00e1s P\u00f3czos"], "End-to-End Differentiable Adversarial Imitation Learning": ["Nir Baram", "Oron Anschel", "Itai Caspi", "Shie Mannor"], "Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning": ["Junhyuk Oh", "Satinder Singh", "Honglak Lee", "Pushmeet Kohli"], "On Context-Dependent Clustering of Bandits": ["Claudio Gentile", "Shuai Li", "Purushottam Kar", "Alexandros Karatzoglou", "Giovanni Zappella", "Evans Etrue Howard"], "Differentiable Programs with Neural Libraries": ["Alex Gaunt", "Marc Brockschmidt", "Nate Kushman", "Daniel Tarlow"], "No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis": ["Rong Ge", "Chi Jin", "Yi Zheng"], "An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis": ["Yuandong Tian"], "Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization": ["Qunwei Li", "Yi Zhou", "Yingbin Liang", "Pramod K Varshney"], "Toward Controlled Generation of Text": ["Zhiting Hu", "Zichao Yang", "Xiaodan Liang", "Ruslan Salakhutdinov", "Eric Xing"], "Strongly-Typed Agents are Guaranteed to Interact Safely": ["David Balduzzi"], "Asynchronous Stochastic Gradient Descent with Delay Compensation": ["Shuxin Zheng", "Qi Meng", "Taifeng Wang", "Wei Chen", "Nenghai Yu", "Zhiming Ma", "Tie-Yan Liu"], "Adaptive Multiple-Arm Identification": ["Jiecao Chen", "Xi Chen", "Qin Zhang", "Yuan Zhou"], "Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control": ["Yunpeng Pan", "Xinyan Yan", "Evangelos Theodorou", "Byron Boots"], "Meritocratic Fairness for Cross-Population Selection": ["Michael Kearns", "Aaron Roth", "Steven Wu"], "Compressed Sensing using Generative Models": ["Ashish Bora", "Ajil Jalal", "Eric Price", "Alexandros Dimakis"], "Online Learning with Local Permutations and Delayed Feedback": ["Liran Szlak", "Ohad Shamir"], "From Patches to Images: A Nonparametric Generative Model": ["Geng Ji", "Michael C. Hughes", "Erik Sudderth"], "Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees": ["Haim Avron", "Michael Kapralov", "Cameron Musco", "Christopher Musco", "Ameya Velingker", "Amir Zandieh"], "Boosted Fitted Q-Iteration": ["Samuele Tosatto", "Matteo Pirotta", "Carlo D'Eramo", "Marcello Restelli"], "Learning Important Features Through Propagating Activation Differences": ["Avanti Shrikumar", "Peyton Greenside", "Anshul Kundaje"], "Deriving Neural Architectures from Sequence and Graph Kernels": ["Tao Lei", "Wengong Jin", "Regina Barzilay", "Tommi Jaakkola"], "Input Convex Neural Networks": ["Brandon Amos", "Lei Xu", "Zico Kolter"], "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks": ["Taeksoo Kim", "Moonsu Cha", "Hyunsoo Kim", "Jungkwon Lee", "Jiwon Kim"], "ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices": ["Chirag Gupta", "ARUN SUGGALA", "Ankit Goyal", "Saurabh Goyal", "Ashish Kumar", "Bhargavi Paranjape", "Harsha Vardhan Simhadri", "Raghavendra Udupa", "Manik Varma", "Prateek Jain"], "State-Frequency Memory Recurrent Neural Networks": ["Hao Hu", "Guo-Jun Qi"], "Multiple Clustering Views from Multiple Uncertain Experts": ["Yale Chang", "Junxiang Chen", "Michael Cho", "Peter Castaldi", "Edwin Silverman", "Jennifer G Dy"], "Adversarial Feature Matching for Text Generation": ["Yizhe Zhang", "Zhe Gan", "Kai Fan", "Zhi Chen", "Ricardo Henao", "Dinghan Shen", "Lawrence Carin"], "Variational Policy for Guiding Point Processes": ["Yichen Wang", "Grady Williams", "Evangelos Theodorou", "Le Song"], "\u201cConvex Until Proven Guilty\u201d: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions": ["Yair Carmon", "John Duchi", "Oliver Hinder", "Aaron Sidford"], "Dictionary Learning Based on Sparse Distribution Tomography": ["Pedram Pad", "Farnood Salehi", "Elisa Celis", "Patrick Thiran", "Michael Unser"], "Distributed Mean Estimation with Limited Communication": ["Ananda Suresh", "Felix Yu", "Sanjiv Kumar", "H. Brendan McMahan"], "Latent Feature Lasso": ["En-Hsu Yen", "Wei-Cheng Lee", "Sung-En Chang", "Arun Suggala", "Shou-De Lin", "Pradeep Ravikumar"], "Learning to Align the Source Code to the Compiled Object Code": ["Dor Levy", "Lior Wolf"], "Continual Learning Through Synaptic Intelligence": ["Friedemann Zenke", "Ben Poole", "Surya Ganguli"], "A Simple Multi-Class Boosting Framework with Theoretical Guarantees and Empirical Proficiency": ["Ron Appel", "Pietro Perona"], "Meta Networks": ["Tsendsuren Munkhdalai", "Hong Yu"], "Scalable Multi-Class Gaussian Process Classification using Expectation Propagation": ["Carlos Villacampa-Calvo", "Daniel Hernandez-Lobato"], "Learning to Aggregate Ordinal Labels by Maximizing Separating Width": ["Guangyong Chen", "Shengyu Zhang", "Di Lin", "Hui Huang", "Pheng Ann Heng"], "On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations": ["Xueyu Mao", "Purnamrita Sarkar", "Deepayan Chakrabarti"], "Max-value Entropy Search for Efficient Bayesian Optimization": ["Zi Wang", "Stefanie Jegelka"], "Scalable Bayesian Rule Lists": ["Hongyu Yang", "Cynthia Rudin", "Margo Seltzer"], "Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning": ["Yevgen Chebotar", "Karol Hausman", "Marvin Zhang", "Gaurav Sukhatme", "Stefan Schaal", "Sergey Levine"], "Automated Curriculum Learning for Neural Networks": ["Alex Graves", "Marc Bellemare", "Jacob Menick", "Remi Munos", "Koray Kavukcuoglu"], "SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization": ["Juyong Kim", "Yookoon Park", "Gunhee Kim", "Sung Ju Hwang"], "A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery": ["Lingxiao Wang", "Xiao Zhang", "Quanquan Gu"], "Understanding Black-box Predictions via Influence Functions": ["Pang Wei Koh", "Percy Liang"], "Differentially Private Submodular Maximization: Data Summarization in Disguise": ["Marko Mitrovic", "Mark Bun", "Andreas Krause", "Amin Karbasi"], "Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics": ["Ken Kansky", "Thomas Silver", "David A M\u00e9ly", "Mohamed Eldawy", "Miguel Lazaro-Gredilla", "Xinghua Lou", "Nimrod Dorfman", "Szymon Sidor", "Scott Phoenix", "Dileep George"], "Local Bayesian Optimization of Motor Skills": ["Riadh Akrour", "Dmitry Sorokin", "Jan Peters", "Gerhard Neumann"], "Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture": ["Mingmin Zhao", "Shichao Yue", "Dina Katabi", "Tommi Jaakkola", "Matt Bianchi"], "Bayesian Models of Data Streams with Hierarchical Power Priors": ["Andres Masegosa", "Thomas D. Nielsen", "Helge Langseth", "Dario Ramos-Lopez", "Antonio Salmeron", "Anders Madsen"], "Latent Intention Dialogue Models": ["Tsung-Hsien Wen", "Yishu Miao", "Phil Blunsom", "Stephen J Young"], "Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability": ["Shayegan Omidshafiei", "Jason Pazis", "Chris Amato", "Jonathan How", "John L Vian"], "Faster Greedy MAP Inference for Determinantal Point Processes": ["Insu Han", "Prabhanjan Kambadur", "Kyoungsoo Park", "Jinwoo Shin"], "Recursive Partitioning for Personalization using Observational Data": ["Nathan Kallus"], "Ordinal Graphical Models: A Tale of Two Approaches": ["ARUN SAI SUGGALA", "Eunho Yang", "Pradeep Ravikumar"], "Scalable Generative Models for Multi-label Learning with Missing Labels": ["Vikas Jain", "Nirbhay Modhe", "Piyush Rai"], "Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible": ["Kai Zheng", "Wenlong Mou", "Liwei Wang"], "Developing Bug-Free Machine Learning Systems With Formal Mathematics": ["Daniel Selsam", "Percy Liang", "David L Dill"], "The Statistical Recurrent Unit": ["Junier Oliva", "Barnab\u00e1s P\u00f3czos", "Jeff Schneider"], "Algebraic Variety Models for High-Rank Matrix Completion": ["Greg Ongie", "Laura Balzano", "Rebecca Willett", "Robert Nowak"], "Fast Bayesian Intensity Estimation for the Permanental Process": ["Christian Walder", "Adrian N Bishop"], "Dropout Inference in Bayesian Neural Networks with Alpha-divergences": ["Yingzhen Li", "Yarin Gal"], "On the Expressive Power of Deep Neural Networks": ["Maithra Raghu", "Ben Poole", "Surya Ganguli", "Jon Kleinberg", "Jascha Sohl-Dickstein"], "Delta Networks for Optimized Recurrent Network Computation": ["Daniel Neil", "Jun Lee", "Tobi Delbruck", "Shih-Chii Liu"], "Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery": ["Mostafa Rahmani", "George Atia"], "Deep Spectral Clustering Learning": ["Marc Law", "Raquel Urtasun", "Zemel Rich"], "Fairness in Reinforcement Learning": ["Shahin Jabbari", "Matthew Joseph", "Michael Kearns", "Jamie Morgenstern", "Aaron Roth"], "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks": ["Chelsea Finn", "Pieter Abbeel", "Sergey Levine"], "Measuring Sample Quality with Kernels": ["Jackson Gorham", "Lester Mackey"], "Robust Probabilistic Modeling with Bayesian Data Reweighting": ["Yixin Wang", "Alp Kucukelbir", "David Blei"], "Coordinated Multi-Agent Imitation Learning": ["Hoang Le", "Yisong Yue", "Peter Carr", "Patrick Lucey"], "Learning to Learn without Gradient Descent by Gradient Descent": ["Yutian Chen", "Matthew Hoffman", "Sergio G\u00f3mez Colmenarejo", "Misha Denil", "Timothy Lillicrap", "Matthew Botvinick", "Nando de Freitas"], "Learning the Structure of Generative Models without Labeled Data": ["Stephen Bach", "Bryan He", "Alexander J Ratner", "Christopher Re"], "Cost-Optimal Learning of Causal Graphs": ["Murat Kocaoglu", "Alexandros Dimakis", "Sriram Vishwanath"], "Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent Coarsening": ["Mohsen Ahmadi Fahandar", "Eyke H\u00fcllermeier", "Ines Couso"], "Consistency Analysis for Binary Classification Revisited": ["Krzysztof Dembczynski", "Wojciech Kotlowski", "Oluwasanmi Koyejo", "Nagarajan Natarajan"], "Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning": ["Oron Anschel", "Nir Baram", "Nahum Shimkin"], "Grammar Variational Autoencoder": ["Matt J. Kusner", "Brooks Paige", "Jose Hernandez-Lobato"], "On Kernelized Multi-armed Bandits": ["Sayak Ray Chowdhury", "Aditya Gopalan"], "Forward and Reverse Gradient-Based Hyperparameter Optimization": ["Luca Franceschi", "Michele Donini", "Paolo Frasconi", "Massimiliano Pontil"], "Image-to-Markup Generation with Coarse-to-Fine Attention": ["Yuntian Deng", "Anssi Kanervisto", "Jeffrey Ling", "Alexander Rush"], "Learning Infinite Layer Networks without the Kernel Trick": ["Roi Livni", "Daniel Carmon", "Amir Globerson"], "A Simulated Annealing Based Inexact Oracle for Wasserstein Loss Minimization": ["Jianbo Ye", "James Wang", "Jia Li"], "A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI": ["Justin Domke"], "Learning to Generate Long-term Future via Hierarchical Prediction": ["Ruben Villegas", "Jimei Yang", "Yuliang Zou", "Sungryull Sohn", "Xunyu Lin", "Honglak Lee"], "Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier": ["Joseph Futoma", "Sanjay Hariharan", "Katherine Heller"], "Deciding How to Decide: Dynamic Routing in Artificial Neural Networks": ["Mason McGill", "Pietro Perona"], "Neural Optimizer Search using Reinforcement Learning": ["Irwan Bello", "Barret Zoph", "Vijay Vasudevan", "Quoc Le"], "Nearly Optimal Robust Matrix Completion": ["Yeshwanth Cherapanamjeri", "Prateek Jain", "Kartik Gupta"], "Learning Discrete Representations via Information Maximizing Self-Augmented Training": ["Weihua Hu", "Takeru Miyato", "Seiya Tokui", "Eiichi Matsumoto", "Masashi Sugiyama"], "Input Switched Affine Networks: An RNN Architecture Designed for Interpretability": ["Jakob Foerster", "Justin Gilmer", "Jan Chorowski", "Jascha Sohl-Dickstein", "David Sussillo"], "Fake News Mitigation via Point Process Based Intervention": ["Mehrdad Farajtabar", "Jiachen Yang", "Xiaojing Ye", "Huan Xu", "Rakshit Trivedi", "Elias Khalil", "Shuang Li", "Le Song", "Hongyuan Zha"], "Co-clustering through Optimal Transport": ["Charlotte Laclau", "Ievgen Redko", "Basarab Matei", "Youn\u00e8s Bennani", "Vincent Brault"], "Adaptive Consensus ADMM for Distributed Optimization": ["Zheng Xu", "Gavin Taylor", "Hao Li", "Mario Figueiredo", "Xiaoming Yuan", "Tom Goldstein"], "Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence": ["Yi Xu", "Qihang Lin", "Tianbao Yang"], "Curiosity-driven Exploration by Self-supervised Prediction": ["Deepak Pathak", "Pulkit Agrawal", "Alexei Efros", "Trevor Darrell"], "Accelerating Eulerian Fluid Simulation With Convolutional Networks": ["Jonathan Tompson", "Kristofer D Schlachter", "Pablo Sprechmann", "Ken Perlin"], "Kernelized Support Tensor Machines": ["Lifang He", "Chun-Ta Lu", "Guixiang Ma", "Shen Wang", "Linlin Shen", "Philip Yu", "Ann Ragin"], "Improving Viterbi is Hard: Better Runtimes Imply Faster Clique Algorithms": ["Arturs Backurs", "Christos Tzamos"], "Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study": ["Samuel Ritter", "David GT Barrett", "Adam Santoro", "Matthew Botvinick"], "Differentially Private Clustering in High-Dimensional Euclidean Spaces": ["Nina Balcan", "Travis Dick", "Yingyu Liang", "Wenlong Mou", "Hongyang Zhang"], "Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs": ["Michael Gygli", "Mohammad Norouzi", "Anelia Angelova"], "Recurrent Highway Networks": ["Julian Zilly", "Rupesh Srivastava", "Jan Koutnik", "J\u00fcrgen Schmidhuber"], "Robust Budget Allocation via Continuous Submodular Functions": ["Matthew J Staib", "Stefanie Jegelka"], "Faster Principal Component Regression and Stable Matrix Chebyshev Approximation": ["Zeyuan Allen-Zhu", "Yuanzhi Li"], "Parallel Multiscale Autoregressive Density Estimation": ["Scott Reed", "A\u00e4ron van den Oord", "Nal Kalchbrenner", "Sergio G\u00f3mez Colmenarejo", "Ziyu Wang", "Yutian Chen", "Dan Belov", "Nando de Freitas"], "Breaking Locality Accelerates Block Gauss-Seidel": ["Stephen Tu", "Shivaram Venkataraman", "Ashia Wilson", "Alex Gittens", "Michael Jordan", "Benjamin Recht"], "Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo": ["Matthew Hoffman"], "Logarithmic Time One-Against-Some": ["Hal Daum\u00e9", "NIKOS KARAMPATZIAKIS", "John Langford", "Paul Mineiro"], "An Adaptive Test of Independence with Analytic Kernel Embeddings": ["Wittawat Jitkrittum", "Zoltan Szabo", "Arthur Gretton"], "Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms": ["Jialei Wang", "Lin Xiao"], "Multi-fidelity Bayesian Optimisation with Continuous Approximations": ["kirthevasan kandasamy", "Gautam Dasarathy", "Barnab\u00e1s P\u00f3czos", "Jeff Schneider"], "Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations": ["Yuanzhi Li", "Yingyu Liang"], "Leveraging Union of Subspace Structure to Improve Constrained Clustering": ["John Lipor", "Laura Balzano"], "An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation": ["David Anderson", "Ming Gu"], "Deep Bayesian Active Learning with Image Data": ["Yarin Gal", "Riashat Islam", "Zoubin Ghahramani"], "Dance Dance Convolution": ["Christopher Donahue", "Zachary Lipton", "Julian McAuley"], "McGan: Mean and Covariance Feature Matching GAN": ["Youssef Mroueh", "Tom Sercu", "Vaibhava Goel"], "Conditional Image Synthesis with Auxiliary Classifier GANs": ["Augustus Odena", "Christopher Olah", "Jon Shlens"], "Active Heteroscedastic Regression": ["Kamalika Chaudhuri", "Prateek Jain", "Nagarajan Natarajan"], "Algorithms for $\\ell_p$ Low-Rank Approximation": ["Flavio Chierichetti", "Sreenivas Gollapudi", "Ravi Kumar", "Silvio Lattanzi", "Rina Panigrahy", "David Woodruff"], "Uniform Convergence Rates for Kernel Density Estimation": ["Heinrich Jiang"], "Bayesian Optimization with Tree-structured Dependencies": ["Rodolphe Jenatton", "Cedric Archambeau", "Javier Gonz\u00e1lez", "Matthias Seeger"], "Deep Transfer Learning with Joint Adaptation Networks": ["Mingsheng Long", "Han Zhu", "Jianmin Wang", "Michael Jordan"], "Lost Relatives of the Gumbel Trick": ["Matej Balog", "Nilesh Tripuraneni", "Zoubin Ghahramani", "Adrian Weller"], "Hierarchy Through Composition with Multitask LMDPs": ["Andrew Saxe", "Adam Earle", "Benjamin Rosman"], "Risk Bounds for Transferring Representations With and Without Fine-Tuning": ["Daniel McNamara", "Nina Balcan"], "Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks": ["Mingyi Hong", "Davood Hajinezhad", "Ming-Min Zhao"], "Robust Structured Estimation with Single-Index Models": ["Sheng Chen", "Arindam Banerjee"], "Deep Tensor Convolution on Multicores": ["David Budden", "Alexander Matveev", "Shibani Santurkar", "Shraman Ray Chaudhuri", "Nir Shavit"], "Variational Inference for Sparse and Undirected Models": ["John Ingraham", "Debora Marks"], "Unifying task specification in reinforcement learning": ["Martha White"], "Axiomatic Attribution for Deep Networks": ["Mukund Sundararajan", "Ankur Taly", "Qiqi Yan"], "PixelCNN Models with Auxiliary Variables for Natural Image Modeling": ["Alexander Kolesnikov", "Christoph Lampert"], "Visualizing and Understanding Multilayer Perceptron Models: A Case Study in Speech Processing": ["Tasha Nagamine", "Nima Mesgarani"], "Unimodal Probability Distributions for Deep Ordinal Classification": ["Christopher Beckham", "Christopher Pal"], "Density Level Set Estimation on Manifolds with DBSCAN": ["Heinrich Jiang"], "Guarantees for Greedy Maximization of Non-submodular Functions with Applications": ["An Bian", "Joachim Buhmann", "Andreas Krause", "Sebastian Tschiatschek"], "ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning": ["Hantian Zhang", "Jerry Li", "Kaan Kara", "Dan Alistarh", "Ji Liu", "Ce Zhang"], "Exact Inference for Integer Latent-Variable Models": ["Kevin Winner", "Debora Sujono", "Daniel Sheldon"], "Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis": ["Ahmed M. Alaa Ibrahim", "Scott B Hu", "Mihaela van der Schaar"], "Understanding Synthetic Gradients and Decoupled Neural Interfaces": ["Wojciech Czarnecki", "Grzegorz \u015awirszcz", "Max Jaderberg", "Simon Osindero", "Oriol Vinyals", "Koray Kavukcuoglu"], "Efficient Online Bandit Multiclass Learning with O(sqrt{T}) Regret": ["Alina Beygelzimer", "Francesco Orabona", "Chicheng Zhang"], "Second-Order Kernel Online Convex Optimization with Adaptive Sketching": ["Daniele Calandriello", "Alessandro Lazaric", "Michal Valko"], "Tensor Decomposition with Smoothness": ["Masaaki Imaizumi", "Kohei Hayashi"], "DeepBach: a Steerable Model for Bach Chorales Generation": ["Ga\u00ebtan HADJERES", "Fran\u00e7ois Pachet", "Frank Nielsen"], "Convolutional Sequence to Sequence Learning": ["Jonas Gehring", "Michael Auli", "David Grangier", "Denis Yarats", "Yann Dauphin"], "Differentially Private Chi-squared Test by Unit Circle Mechanism": ["Kazuya Kakizaki", "Kazuto Fukuchi", "Jun Sakuma"], "Enumerating Distinct Decision Trees": ["Salvatore Ruggieri"], "Large-Scale Evolution of Image Classifiers": ["Esteban Real", "Sherry Moore", "Andrew Selle", "Saurabh Saxena", "Yutaka Leon Suematsu", "Jie Tan", "Quoc Le", "Alexey Kurakin"], "OptNet: Differentiable Optimization as a Layer in Neural Networks": ["Brandon Amos", "Zico Kolter"], "Learning Continuous Semantic Representations of Symbolic Expressions": ["Miltiadis Allamanis", "pankajan Chanthirasegaran", "Pushmeet Kohli", "Charles Sutton"], "Tensor Decomposition via Simultaneous Power Iteration": ["Poan Wang", "Chi-Jen Lu"], "Count-Based Exploration with Neural Density Models": ["Georg Ostrovski", "Marc Bellemare", "A\u00e4ron van den Oord", "Remi Munos"], "Analytical Guarantees on Numerical Precision of Deep Neural Networks": ["Charbel Sakr", "Yongjune Kim", "Naresh Shanbhag"], "Iterative Machine Teaching": ["Weiyang Liu", "Bo Dai", "Ahmad Humayun", "Charlene Tay", "Chen Yu", "Linda Smith", "James Rehg", "Le Song"], "Parseval Networks: Improving Robustness to Adversarial Examples": ["Moustapha Cisse", "Piotr Bojanowski", "Edouard Grave", "Yann Dauphin", "Nicolas Usunier"], "Decoupled Neural Interfaces using Synthetic Gradients": ["Max Jaderberg", "Wojciech Czarnecki", "Simon Osindero", "Oriol Vinyals", "Alex Graves", "David Silver", "Koray Kavukcuoglu"], "Self-Paced Co-training": ["Fan Ma", "Deyu Meng", "Qi Xie", "Zina Li", "Xuanyi Dong"], "SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling": ["Jun-ichiro Hirayama", "Aapo Hyv\u00e4rinen", "Motoaki Kawanabe"], "Combined Group and Exclusive Sparsity for Deep Neural Networks": ["jaehong yoon", "Sung Ju Hwang"], "Local-to-Global Bayesian Network Structure Learning": ["Tian Gao", "Kshitij Fadnis", "Murray Campbell"], "On Calibration of Modern Neural Networks": ["Chuan Guo", "Geoff Pleiss", "Yu Sun", "Kilian Weinberger"], "Active Learning for Cost-Sensitive Classification": ["Akshay Krishnamurthy", "Alekh Agarwal", "Tzu-Kuo Huang", "Hal Daum\u00e9 III", "John Langford"], "Bidirectional learning for time-series models with hidden units": ["Takayuki Osogami", "Hiroshi Kajino", "Taro Sekiyama"], "Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares": ["Junqi Tang", "Mohammad Golbabaee", "Michael E Davies"], "Reinforcement Learning with Deep Energy-Based Policies": ["Tuomas Haarnoja", "Haoran Tang", "Pieter Abbeel", "Sergey Levine"], "Optimal Densification for Fast and Accurate Minwise Hashing": ["Anshumali Shrivastava"], "Learning Determinantal Point Processes with Moments and Cycles": ["John C Urschel", "Ankur Moitra", "Philippe Rigollet", "Victor-Emmanuel Brunel"], "Sequence Tutor: Conservative fine-tuning of sequence generation models with KL-control": ["Natasha Jaques", "Shixiang Gu", "Dzmitry Bahdanau", "Jose Hernandez-Lobato", "Richard E Turner", "Douglas Eck"], "Deep Generative Models for Relational Data with Side Information": ["Changwei Hu", "Piyush Rai", "Lawrence Carin"], "Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for MCMC": ["Umut Simsekli"], "Variational Dropout Sparsifies Deep Neural Networks": ["Dmitry Molchanov", "Arsenii Ashukha", "Dmitry Vetrov"], "How to Escape Saddle Points Efficiently": ["Chi Jin", "Rong Ge", "Praneeth Netrapalli", "Sham M. Kakade", "Michael Jordan"], "Stochastic DCA for the Large-sum of Non-convex Functions Problem and its Application to Group Variable Selection in Classification": ["Hoai An Le Thi", "Hoai Minh Le", "Duy Nhat Phan", "Bach Tran"], "Dissipativity Theory for Nesterov's Accelerated Method": ["Bin Hu", "Laurent Lessard"], "RobustFill: Neural Program Learning under Noisy I/O": ["Jacob Devlin", "Jonathan Uesato", "Surya Bhupatiraju", "Rishabh Singh", "Abdelrahman Mohammad", "Pushmeet Kohli"], "Multichannel End-to-end Speech Recognition": ["Tsubasa Ochiai", "Shinji Watanabe", "Takaaki Hori", "John Hershey"], "Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks": ["Lars Mescheder", "Sebastian Nowozin", "Andreas Geiger"], "Estimating individual treatment effect: generalization bounds and algorithms": ["Uri Shalit", "Fredrik D Johansson", "David Sontag"], "Online Partial Least Square Optimization: Dropping Convexity for Better Efficiency and Scalability": ["Zhehui Chen", "Lin Yang", "Chris Junchi Li", "Tuo Zhao"], "Batched High-dimensional Bayesian Optimization via Structural Kernel Learning": ["Zi Wang", "Chengtao Li", "Stefanie Jegelka", "Pushmeet Kohli"], "The loss surface of deep and wide neural networks": ["Quynh Nguyen", "Matthias Hein"], "Diameter-Based Active Learning": ["Christopher Tosh", "Sanjoy Dasgupta"], "Wasserstein Generative Adversarial Networks": ["Martin Arjovsky", "Soumith Chintala", "L\u00e9on Bottou"], "Coresets for Vector Summarization with Applications to Network Graphs": ["Dan Feldman", "Sedat Ozer", "Daniela Rus"], "Tensor-Train Recurrent Neural Networks for Video Classification": ["Yinchong Yang", "Denis Krompass", "Volker Tresp"], "Automatic Discovery of the Statistical Types of Variables in a Dataset": ["Isabel Valera", "Zoubin Ghahramani"], "Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization": ["Qi Lei", "En-Hsu Yen", "Chao-Yuan Wu", "Inderjit Dhillon", "Pradeep Ravikumar"], "Regularising Non-linear Models Using Feature Side-information": ["Amina Mollaysa", "Pablo Strasser", "Alexandros Kalousis"], "Deletion-Robust Submodular Maximization: Data Summarization with \"the Right to be Forgotten\"": ["Baharan Mirzasoleiman", "Amin Karbasi", "Andreas Krause"], "Innovation Pursuit: A New Approach to the Subspace Clustering Problem": ["Mostafa Rahmani", "George Atia"], "Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP": ["Satyen Kale", "Zohar Karnin", "Tengyuan Liang", "David Pal"], "Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates": ["Jiali Mei", "Yohann De Castro", "Yannig Goude", "Georges H\u00e9brail"], "Video Pixel Networks": ["Nal Kalchbrenner", "Karen Simonyan", "A\u00e4ron van den Oord", "Ivo Danihelka", "Oriol Vinyals", "Alex Graves", "Koray Kavukcuoglu"], "Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks": ["David Balduzzi", "Brian McWilliams", "Tony Butler-Yeoman"], "Warped Convolutions: Efficient Invariance to Spatial Transformations": ["Joao Henriques", "Andrea Vedaldi"], "Learning Texture Manifolds with the Periodic Spatial GAN": ["Urs M Bergmann", "Nikolay Jetchev", "Roland Vollgraf"], "meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting": ["Xu SUN", "Xuancheng REN", "Shuming Ma", "Houfeng Wang"], "Joint Dimensionality Reduction and Metric Learning: A Geometric Take": ["Mehrtash Harandi", "Mathieu Salzmann", "Richard I Hartley"], "High-dimensional Non-Gaussian Single Index Models via Thresholded Score Function Estimation": ["Zhuoran Yang", "Krishnakumar Balasubramanian", "Han Liu"], "Deep Voice: Real-time Neural Text-to-Speech": ["Andrew Gibiansky", "Mike Chrzanowski", "Mohammad Shoeybi", "Shubho Sengupta", "Gregory Diamos", "Sercan Arik", "Jonathan Raiman", "John Miller", "Xian Li", "Yongguo Kang", "Adam Coates", "Andrew Ng"], "Bottleneck Conditional Density Estimation": ["Rui Shu", "Hung Bui", "Mohammad Ghavamzadeh"], "Interactive Learning from Policy-Dependent Human Feedback": ["James MacGlashan", "Mark Ho", "Robert Loftin", "Bei Peng", "Guan Wang", "David L Roberts", "Matthew E. Taylor", "Michael L. Littman"], "Stochastic modified equations and adaptive stochastic gradient algorithms": ["Qianxiao Li", "Cheng Tai", "Weinan E"], "Data-Efficient Policy Evaluation Through Behavior Policy Search": ["Josiah Hanna", "Philip S. Thomas", "Peter Stone", "Scott Niekum"], "Graph-based Isometry Invariant Representation Learning": ["Renata Khasanova", "Pascal Frossard"], "Capacity Releasing Diffusion for Speed and Locality.": ["Di Wang", "Kimon Fountoulakis", "Monika Henzinger", "Michael Mahoney", "Satish Rao"], "High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm": ["Rongda Zhu", "Lingxiao Wang", "Chengxiang Zhai", "Quanquan Gu"], "Lazifying Conditional Gradient Algorithms": ["G\u00e1bor Braun", "Sebastian Pokutta", "Daniel Zink"], "Uncovering Causality from Multivariate Hawkes Integrated Cumulants": ["Massil Achab", "Emmanuel Bacry", "St\u00e9phane Ga\u00efffas", "Iacopo Mastromatteo", "Jean-Fran\u00e7ois Muzy"], "Frame-based Data Factorizations": ["Sebastian Mair", "Ahc\u00e8ne Boubekki", "Ulf Brefeld"], "Asymmetric Tri-training for Unsupervised Domain Adaptation": ["Kuniaki Saito", "Yoshitaka Ushiku", "Tatsuya Harada"], "Depth-Width Tradeoffs in Approximating Natural Functions With Neural Networks": ["Itay Safran", "Ohad Shamir"], "Partitioned Tensor Factorizations for Learning Mixed Membership Models": ["Zilong Tan", "Sayan Mukherjee"], "Priv\u2019IT: Private and Sample Efficient Identity Testing": ["Bryan Cai", "Constantinos Daskalakis", "Gautam Kamath"], "Identifying Best Interventions through Online Importance Sampling": ["Rajat Sen", "Karthikeyan Shanmugam", "Alexandros Dimakis", "Sanjay Shakkottai"], "Minimax Regret Bounds for Reinforcement Learning": ["Mohammad Gheshlaghi Azar", "Ian Osband", "Remi Munos"], "Efficient Nonmyopic Active Search": ["Shali Jiang", "Luiz Gustavo Malkomes", "Geoff Converse", "Alyssa Shofner", "Benjamin Moseley", "Roman Garnett"], "Why is Posterior Sampling Better than Optimism for Reinforcement Learning?": ["Ian Osband", "Benjamin Van Roy"], "Efficient Distributed Learning with Sparsity": ["Jialei Wang", "Mladen Kolar", "Nati Srebro", "Tong Zhang"], "Hyperplane Clustering Via Dual Principal Component Pursuit": ["Manolis Tsakiris", "Rene Vidal"], "Magnetic Hamiltonian Monte Carlo": ["Nilesh Tripuraneni", "Mark Rowland", "Zoubin Ghahramani", "Richard E Turner"], "Prediction and Control with Temporal Segment Models": ["Nikhil Mishra", "Pieter Abbeel", "Igor Mordatch"], "Differentially Private Learning of Graphical Models using CGMs": ["Garrett Bernstein", "Ryan McKenna", "Tao Sun", "Daniel Sheldon", "Michael Hay", "Gerome Miklau"], "Learning Hierarchical Features from Deep Generative Models": ["Shengjia Zhao", "Jiaming Song", "Stefano Ermon"], "Differentially Private Ordinary Least Squares": ["Or Sheffet"], "Active Learning for Accurate Estimation of Linear Models": ["Carlos Riquelme Ruiz", "Mohammad Ghavamzadeh", "Alessandro Lazaric"], "Stochastic Generative Hashing": ["Bo Dai", "Ruiqi Guo", "Sanjiv Kumar", "Niao He", "Le Song"], "Clustering by Sum of Norms: Stochastic Incremental Algorithm, Convergence and Cluster Recovery": ["Ashkan Panahi", "Devdatt Dubhashi", "Fredrik D Johansson", "Chiranjib Bhattacharya"], "Practical Gauss-Newton Optimisation for Deep Learning": ["Aleksandar Botev", "Julian Hippolyt Ritter", "David Barber"], "Consistent On-Line Off-Policy Evaluation": ["Assaf Hallak", "Shie Mannor"], "Multilevel Clustering via Wasserstein Means": ["Nhat Ho", "Long Nguyen", "Mikhail Yurochkin", "Hung Bui", "Viet Huynh", "Dinh Phung"], "Multiplicative Normalizing Flows for Variational Bayesian Neural Networks": ["Christos Louizos", "Max Welling"], "A Distributional Perspective on Reinforcement Learning": ["Marc Bellemare", "Will Dabney", "Remi Munos"], "Counterfactual Data-Fusion for Online Reinforcement Learners": ["Andrew Forney", "Judea Pearl", "Elias Bareinboim"], "FeUdal Networks for Hierarchical Reinforcement Learning": ["Alexander Vezhnevets", "Simon Osindero", "Tom Schaul", "Nicolas Heess", "Max Jaderberg", "David Silver", "Koray Kavukcuoglu"], "Clustering High Dimensional Dynamic Data Streams": ["Lin Yang", "Harry Lang", "Christian Sohler", "Vladimir Braverman", "Gereon Frahling"], "Stochastic Gradient Monomial Gamma Sampler": ["Yizhe Zhang", "Changyou Chen", "Zhe Gan", "Ricardo Henao", "Lawrence Carin"], "On Relaxing Determinism in Arithmetic Circuits": ["Arthur Choi", "Adnan Darwiche"], "Analysis and Optimization of Graph Decompositions by Lifted Multicuts": ["Andrea Hornakova", "Jan-Hendrik Lange", "Bjoern Andres"], "Modular Multitask Reinforcement Learning with Policy Sketches": ["Jacob Andreas", "Dan Klein", "Sergey Levine"], "Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs": ["Rakshit Trivedi", "Hajun Dai", "Yichen Wang", "Le Song"], "Adaptive Sampling Probabilities for Non-Smooth Optimization": ["Hongseok Namkoong", "Aman Sinha", "Steven Yadlowsky", "John Duchi"], "Latent LSTM Allocation: Joint clustering and non-linear dynamic modeling of sequence data": ["Manzil Zaheer", "Amr Ahmed", "Alex Smola"], "Fast k-Nearest Neighbour Search via Prioritized DCI": ["Ke Li", "Jitendra Malik"], "The Predictron:  End-To-End Learning and Planning": ["David Silver", "Hado van Hasselt", "Matteo Hessel", "Tom Schaul", "Arthur Guez", "Tim Harley", "Gabriel Dulac-Arnold", "David Reichert", "Neil Rabinowitz", "Andre Barreto", "Thomas Degris"], "Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders": ["Cinjon Resnick", "Adam Roberts", "Jesse Engel", "Douglas Eck", "Sander Dieleman", "Karen Simonyan", "Mohammad Norouzi"], "The Price of Differential Privacy For Online Learning": ["Naman Agarwal", "Karan Singh"], "High Dimensional Bayesian Optimization with Elastic Gaussian Process": ["Santu Rana", "Cheng Li", "Sunil Gupta", "Vu Nguyen", "Svetha Venkatesh"], "Probabilistic Path Hamiltonian Monte Carlo": ["Vu Dinh", "Arman Bilge", "Cheng Zhang", "Frederick Matsen"], "Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs": ["Alon Brutzkus", "Amir Globerson"], "On orthogonality and learning RNNs with long term dependencies": ["Eugene Vorontsov", "Chiheb Trabelsi", "Christopher Pal", "Samuel Kadoury"], "Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement": ["Jonathan Eckstein", "Noam Goldberg", "Ai Kagawa"], "How Close Are the Eigenvectors of the Sample and Actual Covariance Matrices?": ["Andreas Loukas"], "Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables": ["Bryant Chen", "Daniel Kumor", "Elias Bareinboim"], "Stochastic Gradient MCMC Methods for Hidden Markov Models": ["Yi-An Ma", "Nicholas J Foti", "Emily Fox"], "Improving Gibbs Sampler Scan Quality with DoGS": ["Ioannis Mitliagkas", "Lester Mackey"], "Contextual Decision Processes with low Bellman rank are PAC-Learnable": ["Nan Jiang", "Akshay Krishnamurthy", "Alekh Agarwal", "John Langford", "Robert Schapire"], "Sharp Minima Can Generalize For Deep Nets": ["Laurent Dinh", "Razvan Pascanu", "Samy Bengio", "Yoshua Bengio"], "Learning to Discover Sparse Graphical Models": ["Eugene Belilovsky", "Kyle Kastner", "Gael Varoquaux", "Matthew B Blaschko"], "Analogical Inference for Multi-relational Embeddings": ["Hanxiao Liu", "Yuexin Wu", "Yiming Yang"], "Adaptive Neural Networks for Efficient Inference": ["Tolga Bolukbasi", "Joseph Wang", "Ofer Dekel", "Venkatesh Saligrama"], "Confident Multiple Choice Learning": ["Kimin Lee", "Changho Hwang", "KyoungSoo Park", "Jinwoo Shin"], "Stochastic  Bouncy  Particle Sampler": ["Ari Pakman", "Dar Gilboa", "David Carlson", "Liam Paninski"], "Post-Inference Prior Swapping": ["William Neiswanger", "Eric Xing"], "Equivariance Through Parameter-Sharing": ["Siamak Ravanbakhsh", "Jeff Schneider", "Barnab\u00e1s P\u00f3czos"], "A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates": ["Tianbao Yang", "Qihang Lin", "Lijun Zhang"], "A Unified View of Multi-Label Performance Measures": ["Xi-Zhu Wu", "Zhi-Hua Zhou"], "Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction": ["Weizhong Zhang", "Bin Hong", "Wei Liu", "Jieping Ye", "Deng Cai", "Xiaofei He", "Jie Wang"], "Tensor Belief Propagation": ["Andrew Wrigley", "Wee Sun Lee", "Nan Ye"], "Dual Supervised Learning": ["Yingce Xia", "Tao Qin", "Wei Chen", "Jiang Bian", "Nenghai Yu", "Tie-Yan Liu"], "Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling": ["Hairong Liu", "Zhenyao Zhu", "Xiangang Li", "Sanjeev Satheesh"], "Consistent k-Clustering": ["Silvio Lattanzi", "Sergei Vassilvitskii"], "Bayesian Boolean Matrix Factorisation": ["Tammo Rukat", "Christopher Holmes", "Michalis Titsias", "Christopher Yau"], "Discovering Discrete Latent Topics with Neural Variational Inference": ["Yishu Miao", "Edward Grefenstette", "Phil Blunsom"], "Efficient softmax approximation for GPUs": ["Edouard Grave", "Armand Joulin", "Moustapha Cisse", "David Grangier", "Herve Jegou"], "Neural networks and rational functions": ["Matus Telgarsky"], "Oracle Complexity of Second-Order Methods for Finite-Sum Problems": ["Yossi Arjevani", "Ohad Shamir"], "Improved Variational Autoencoders for Text Modeling using Dilated Convolutions": ["Zichao Yang", "Zhiting Hu", "Ruslan Salakhutdinov", "Taylor Berg-Kirkpatrick"], "A Semismooth Newton Method for Fast, Generic Convex Programming": ["Alnur Ali", "Eric Wong", "Zico Kolter"], "Constrained Policy Optimization": ["Joshua Achiam", "David Held", "Aviv Tamar", "Pieter Abbeel"], "Minimizing Trust Leaks for Robust Sybil Detection": ["J\u00e1nos H\u00f6ner", "Shinichi Nakajima", "Alexander Bauer", "Klaus-robert Mueller", "Nico G\u00f6rnitz"], "Tight Bounds for Approximate Carath\u00e9odory and Beyond": ["Vahab Mirrokni", "Renato Leme", "Adrian Vladu", "Sam Wong"], "Multi-objective Bandits: Optimizing the Generalized Gini Index": ["Robert Busa-Fekete", "Balazs Szorenyi", "Paul Weng", "Shie Mannor"], "Soft-DTW: a Differentiable Loss Function for Time-Series": ["Marco Cuturi", "Mathieu Blondel"], "Projection-free Distributed Online Learning in Networks": ["Wenpeng Zhang", "Peilin Zhao", "wenwu zhu", "Steven Hoi", "Tong Zhang"], "Safety-Aware Algorithms for Adversarial Contextual Bandit": ["Wen Sun", "Debadeepta Dey", "Ashish Kapoor"], "World of Bits: An Open-Domain Platform for Web-Based Agents": ["Tim Shi", "Andrej Karpathy", "Linxi Fan", "Jonathan Hernandez", "Percy Liang"], "Preferential Bayesian Optmization": ["Javier Gonz\u00e1lez", "Zhenwen Dai", "Andreas Damianou", "Neil Lawrence"], "Deep IV: A Flexible Approach for Counterfactual Prediction": ["Jason Hartford", "Greg Lewis", "Kevin Leyton-Brown", "Matt Taddy"], "Provably Optimal Algorithms for Generalized Linear Contextual Bandits": ["Lihong Li", "Yu Lu", "Dengyong Zhou"], "Algorithmic Stability and Hypothesis Complexity": ["Tongliang Liu", "G\u00e1bor Lugosi", "Gergely Neu", "Dacheng Tao"], "Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use": ["Vatsal Sharan", "Gregory Valiant"], "Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks": ["Kevin Scaman", "Francis Bach", "Sebastien Bubeck", "Yin Tat Lee", "Laurent Massouli\u00e9"], "Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank": ["Liang Zhao", "Siyu Liao", "Yanzhi Wang", "Zhe Li", "Jian Tang", "Bo Yuan"], "Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis": ["Dan Garber", "Ohad Shamir", "Nati Srebro"], "Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method": ["Chenzi Zhang", "Shuguang Hu", "Zhihao Gavin Tang", "Hubert Chan"], "Gradient Boosted Decision Trees for High Dimensional Sparse Output": ["Si Si", "Huan Zhang", "Sathiya Keerthi", "Dhruv Mahajan", "Inderjit Dhillon", "Cho-Jui Hsieh"], "Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions": ["Yichen Chen", "Dongdong Ge", "Mengdi Wang", "Zizhuo Wang", "Yinyu Ye", "Hao Yin"], "Attentive Recurrent Comparators": ["Pranav Shyam", "Shubham Gupta", "Ambedkar Dukkipati"], "Conditional Accelerated Lazy Stochastic Gradient Descent": ["Guanghui ", "Sebastian Pokutta", "Yi Zhou", "Daniel Zink"], "Neural Message Passing for Quantum Chemistry": ["Justin Gilmer", "Samuel Schoenholz", "Patrick F Riley", "Oriol Vinyals", "George Dahl"], "Uniform Deviation Bounds for k-Means Clustering": ["Olivier Bachem", "Mario Lucic", "Hamed Hassani", "Andreas Krause"], "Nystr\u00f6m Method with Kernel K-means++ Samples as Landmarks": ["Dino Oglic", "Thomas Gaertner"], "Learning Stable Stochastic Nonlinear Dynamical Systems": ["Jonas Umlauft", "Sandra Hirche"], "Model-Independent Online Learning for Influence Maximization": ["Sharan Vaswani", "Branislav Kveton", "Zheng Wen", "Mohammad Ghavamzadeh", "Laks V.S Lakshmanan", "Mark Schmidt"], "Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values": ["Chaoxu Zhou", "Wenbo Gao", "Donald Goldfarb"], "Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data": ["XIUYAN NI", "Novi Quadrianto", "Yusu Wang", "Chao Chen"], "Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning": ["Jakob Foerster", "Nantas Nardelli", "Gregory Farquhar", "Triantafyllos Afouras", "Phil Torr", "Pushmeet Kohli", "Shimon Whiteson"], "On The Projection Operator to A Three-view Cardinality Constrained Set": ["Haichuan Yang", "Shupeng Gui", "Chuyang Ke", "Daniel Stefankovic", "Ryohei Fujimaki", "Ji Liu"], "Near-Optimal Design of Experiments via Regret Minimization": ["Zeyuan Allen-Zhu", "Yuanzhi Li", "Aarti Singh", "Yining Wang"], "Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs": ["Li Jing", "Yichen Shen", "Tena Dubcek", "John E Peurifoy", "Scott Skirlo", "Yann LeCun", "Max Tegmark", "Marin Solja\\v{c}i\\'{c}"], "End-to-End Learning for Structured Prediction Energy Networks": ["David Belanger", "Bishan Yang", "Andrew McCallum"], "Globally Induced Forest: A Prepruning Compression Scheme": ["Jean-Michel Begon", "Arnaud Joly", "Pierre Geurts"], "Identify the Nash Equilibrium in Static Games with Random Payoffs": ["Yichi Zhou", "Jialian Li", "Jun Zhu"], "Neural Episodic Control": ["Alexander Pritzel", "Benigno Uria", "Srinivasan Sriram", "Adri\u00e0 Puigdomenech Badia", "Oriol Vinyals", "Demis Hassabis", "Daan Wierstra", "Charles Blundell"]}, {"When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\\ell_2$-consistency and Neuroscience Applications": ["Healthcare"], "ChoiceRank: Identifying Preferences from Node Traffic in Networks": ["Ranking and preferences"], "iSurvive: An Interpretable, Event-time Prediction Model for mHealth": ["Healthcare"], "Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space": ["Bayesian Optimization"], "A Closer Look at Memorization in Deep Networks": ["Deep learning 7: analysis"], "Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data": ["Robust Estimation"], "Approximate Steepest Coordinate Descent": ["Continuous optimization 5"], "The Shattered Gradients Problem: If resnets are the answer, then what is the question?": ["Deep learning theory 1"], "Recovery Guarantees for One-hidden-layer Neural Networks": ["Deep learning theory 2"], "Reduced Space and Faster Convergence in Imperfect-Information Games via Pruning": ["Game theory and multiagents"], "MEC: Memory-efficient Convolution for Deep Neural Network": ["Deep learning 8: hardware"], "A Birth-Death Process for Feature Allocation": ["Bayesian Nonparametrics"], "Pain-Free Random Differential Privacy with Sensitivity Sampling": ["Privacy and security 2"], "Programming with a Differentiable Forth Interpreter": ["ML and programming"], "Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution": ["Continuous control"], "Robust Guarantees of Stochastic Greedy Algorithms": ["Combinatorial optimization 1"], "Sequence Modeling via Segmentations": ["Recurrent neural networks 4"], "Bayesian inference on random simple graphs with power law degree distributions": ["Networks and relational learning"], "Tensor Balancing on Statistical Manifold": ["Continuous optimization 4"], "Generalization and Equilibrium in Generative Adversarial Nets (GANs)": ["Deep generative models 2"], "The Sample Complexity of Online One-Class Collaborative Filtering": ["Online learning 1"], "Gradient Coding: Avoiding Stragglers in Distributed Learning": ["Infomation theory"], "Connected Subgraph Detection with Mirror Descent on SDPs": ["Continuous optimization 2"], "Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC": ["Monte Carlo methods 2"], "Regret Minimization in Behaviorally-Constrained Zero-Sum Games": ["Game theory and multiagents"], "Asynchronous Distributed Variational Gaussian Processes for Regression": ["Gaussian processes"], "Random Feature Expansions for Deep Gaussian Processes": ["Gaussian processes"], "Leveraging Node Attributes for Incomplete Relational Data": ["Networks and relational learning"], "Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference": ["Causal Inference 1"], "Evaluating the Variance of Likelihood-Ratio Gradient Estimators": ["Deep learning 1: backprop"], "Efficient Regret Minimization in Non-Convex Games": ["Online learning 2"], "Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU": ["Online learning 2"], "Canopy --- Fast Sampling with Cover Trees": ["Monte Carlo methods 1"], "Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation": ["Supervised learning 1"], "Robust Submodular Maximization: A Non-Uniform Partitioning Approach": ["Combinatorial optimization 1"], "Dynamic Word Embeddings": ["Language 1"], "Robust Adversarial Reinforcement Learning": ["Reinforcement learning 1"], "Multi-Class Optimal Margin Distribution Machine": ["Supervised learning 1"], "Just Sort It! A Simple and Effective Approach to Active Preference Learning": ["Ranking and preferences"], "Zero-Inflated Exponential Family Embeddings": ["Deep generative models 3"], "Variational Boosting: Iteratively Refining Posterior Approximations": ["Probabilistic inference 3"], "Convexified Convolutional Neural Networks": ["Deep learning theory 3"], "Geometry of Neural Network Loss Surfaces via Random Matrix Theory": ["Deep learning theory 1"], "Follow the Moving Leader in Deep Learning": ["Deep learning theory 2"], "Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections": ["Recurrent neural networks 2"], "Coupling Distributed and Symbolic Execution for Natural Language Queries": ["Language 1"], "Distributed and Provably Good Seedings for k-Means in Constant Rounds": ["Clustering 1"], "Learning Hawkes Processes from Short Doubly-Censored Event Sequences": ["Time series"], "A Laplacian Framework for Option Discovery in Reinforcement Learning": ["Reinforcement learning 4"], "Spherical Structured Feature Maps for Kernel Approximation": ["Kernel methods"], "Probabilistic Submodular Maximization in Sub-Linear Time": ["Combinatorial optimization 1"], "Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction": ["Structured prediction"], "Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition": ["Spectral methods"], "Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering": ["Clustering 1"], "Dueling Bandits with Weak Regret": ["Online learning 3"], "Optimal and Adaptive Off-policy Evaluation in Contextual Bandits": ["Reinforcement learning 5"], "Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter": ["Continuous optimization 7"], "Variants of RMSProp and Adagrad with Logarithmic Regret Bounds": ["Online learning 4"], "Being Robust (in High Dimensions) Can Be Practical": ["High dimensional estimation"], "Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things": ["Supervised learning 1"], "Learned Optimizers that Scale and Generalize": ["Deep learning 4: learning to learn"], "An Infinite Hidden Markov Model With Similarity-Biased Transitions": ["Bayesian Nonparametrics"], "Zonotope hit-and-run for efficient sampling from projection DPPs": ["Probabilistic inference 2"], "DARLA: Improving Zero-Shot Transfer in Reinforcement Learning": ["Reinforcement learning 3"], "Online and Linear-Time Attention by Enforcing Monotonic Alignments": ["Recurrent neural networks 3"], "Learning Latent Space Models with Angular Constraints": ["Probabilistic inference 3"], "SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient": ["Continuous optimization 5"], "Beyond Filters: Compact Feature Map for Portable Deep Model": ["Deep learning 8: hardware"], "High-Dimensional Structured Quantile Regression": ["High dimensional estimation"], "Multi-task Learning with Labeled and Unlabeled Tasks": ["Transfer and multitask learning"], "GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization": ["Continuous optimization 2"], "Language Modeling with Gated Convolutional Networks": ["Language 3"], "Learning Gradient Descent: Better Generalization and Longer Horizons": ["Deep learning 4: learning to learn"], "Sequence to Better Sequence: Continuous Revision of Combinatorial Structures": ["Recurrent neural networks 4"], "Distributed Batch Gaussian Process Optimization": ["Gaussian processes"], "Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data": ["Semisupervised and curriculum learning"], "Online Learning to Rank in Stochastic Click Models": ["Online learning 1"], "Exact MAP Inference by Avoiding Fractional Vertices": ["Probabilistic inference 1"], "Forest-type Regression with General Losses and Robust Forest": ["Ensemble methods"], "Uncorrelation and Evenness: a New Diversity-Promoting Regularizer": ["Probabilistic inference 3"], "Coherent probabilistic forecasts for hierarchical time series": ["Time series"], "Evaluating Bayesian Models with Posterior Dispersion Indices": ["Probabilistic learning 1"], "Failures of Gradient-Based Deep Learning": ["Deep learning theory 2"], "Global optimization of Lipschitz functions": ["Continuous optimization 1"], "Approximate Newton Methods and Their Local Convergence": ["Continuous optimization 4"], "An Alternative Softmax Operator for Reinforcement Learning": ["Reinforcement learning 2"], "A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions": ["Infomation theory"], "Selective Inference for Sparse High-Order Interaction Models": ["Sparsity 2"], "Real-Time Adaptive Image Compression": ["Applications"], "Robust Gaussian Graphical Model Estimation with Arbitrary Corruption": ["Robust Estimation"], "Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity": ["Sparsity 1"], "On the Sampling Problem for Kernel Quadrature": ["Probabilistic inference 2"], "Spectral Learning from a Single Trajectory under Finite-State Policies": ["Spectral methods"], "Relative Fisher Information and Natural Gradient for Learning Large Modular Models": ["Deep learning 5: Fisher approximations"], "Learning Deep Architectures via Generalized Whitened Neural Networks": ["Deep learning 5: Fisher approximations"], "Learning Algorithms for Active Learning": ["Deep learning 4: learning to learn"], "Convex Phase Retrieval without Lifting via PhaseMax": ["Continuous optimization 3"], "Sliced Wasserstein Kernel for Persistence Diagrams": ["Kernel methods"], "Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression": ["Transfer and multitask learning"], "Device Placement Optimization with Reinforcement Learning": ["Deep learning 8: hardware"], "Emulating the Expert: Inverse Optimization through Online Learning": ["Online learning 4"], "Estimating the unseen from multiple populations": ["Learning theory 1"], "Multilabel Classification with Group Testing and Codes": ["High dimensional estimation"], "Unsupervised Learning by Predicting Noise": ["Deep learning 2: invariances"], "Adapting Kernel Representations Online Using Submodular Maximization": ["Kernel methods"], "Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization": ["Sparsity 1"], "AdaNet: Adaptive Structural Learning of Artificial Neural Networks": ["Deep learning 3: metalearning"], "Sub-sampled Cubic Regularization for Non-convex Optimization": ["Continuous optimization 7"], "StingyCD: Safely Avoiding Wasteful Updates in Coordinate Descent": ["Continuous optimization 5"], "Learning in POMDPs with Monte Carlo Tree Search": ["Reinforcement learning 3"], "Test of Time Award": ["Test of Time Award"], "On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit": ["Sparsity 1"], "Active Learning for Top-$K$ Rank Aggregation from Noisy Comparisons": ["Ranking and preferences"], "On Approximation Guarantees for Greedy Low Rank Optimization": ["Combinatorial optimization 1"], "Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging": ["Learning theory 1"], "Maximum Selection and Ranking under Noisy Comparisons": ["Ranking and preferences"], "Stochastic Variance Reduction Methods for Policy Evaluation": ["Reinforcement learning 5"], "Nonparanormal Information Estimation": ["Infomation theory"], "End-to-End Differentiable Adversarial Imitation Learning": ["Reinforcement learning 3"], "Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning": ["Deep reinforcement learning 1"], "On Context-Dependent Clustering of Bandits": ["Online learning 3"], "Differentiable Programs with Neural Libraries": ["ML and programming"], "No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis": ["Matrix factorization 2"], "An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis": ["Continuous optimization 6"], "Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization": ["Continuous optimization 7"], "Toward Controlled Generation of Text": ["Language 2"], "Strongly-Typed Agents are Guaranteed to Interact Safely": ["Game theory and multiagents"], "Asynchronous Stochastic Gradient Descent with Delay Compensation": ["Distributed optimization"], "Adaptive Multiple-Arm Identification": ["Online learning 3"], "Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control": ["Continuous control"], "Meritocratic Fairness for Cross-Population Selection": ["Learning theory 1"], "Compressed Sensing using Generative Models": ["Sparsity 1"], "Online Learning with Local Permutations and Delayed Feedback": ["Online learning 1"], "From Patches to Images: A Nonparametric Generative Model": ["Bayesian Nonparametrics"], "Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees": ["Supervised learning 2"], "Boosted Fitted Q-Iteration": ["Reinforcement learning 1"], "Learning Important Features Through Propagating Activation Differences": ["Deep learning 1: backprop"], "Deriving Neural Architectures from Sequence and Graph Kernels": ["Deep learning 2: invariances"], "Input Convex Neural Networks": ["Deep learning 6"], "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks": ["Deep generative models 2"], "ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices": ["Metric learning"], "State-Frequency Memory Recurrent Neural Networks": ["Recurrent neural networks 1"], "Multiple Clustering Views from Multiple Uncertain Experts": ["Clustering 2"], "Adversarial Feature Matching for Text Generation": ["Language 2"], "Variational Policy for Guiding Point Processes": ["Time series"], "\u201cConvex Until Proven Guilty\u201d: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions": ["Continuous optimization 7"], "Dictionary Learning Based on Sparse Distribution Tomography": ["Sparsity 2"], "Distributed Mean Estimation with Limited Communication": ["Infomation theory"], "Latent Feature Lasso": ["Latent feature models"], "Learning to Align the Source Code to the Compiled Object Code": ["ML and programming"], "Continual Learning Through Synaptic Intelligence": ["Deep learning 5: Fisher approximations"], "A Simple Multi-Class Boosting Framework with Theoretical Guarantees and Empirical Proficiency": ["Ensemble methods"], "Meta Networks": ["Deep learning 3: metalearning"], "Scalable Multi-Class Gaussian Process Classification using Expectation Propagation": ["Gaussian processes"], "Learning to Aggregate Ordinal Labels by Maximizing Separating Width": ["Probabilistic inference 3"], "On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations": ["Matrix factorization 1"], "Max-value Entropy Search for Efficient Bayesian Optimization": ["Bayesian Optimization"], "Scalable Bayesian Rule Lists": ["Probabilistic learning 2"], "Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning": ["Continuous control"], "Automated Curriculum Learning for Neural Networks": ["Semisupervised and curriculum learning"], "SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization": ["Deep learning 3: metalearning"], "A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery": ["Matrix factorization 3"], "Understanding Black-box Predictions via Influence Functions": ["Supervised learning 2"], "Differentially Private Submodular Maximization: Data Summarization in Disguise": ["Privacy and security 1"], "Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics": ["Transfer and multitask learning"], "Local Bayesian Optimization of Motor Skills": ["Continuous control"], "Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture": ["Healthcare"], "Bayesian Models of Data Streams with Hierarchical Power Priors": ["Probabilistic learning 1"], "Latent Intention Dialogue Models": ["Language 2"], "Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability": ["Game theory and multiagents"], "Faster Greedy MAP Inference for Determinantal Point Processes": ["Probabilistic inference 2"], "Recursive Partitioning for Personalization using Observational Data": ["Causal Inference 2"], "Ordinal Graphical Models: A Tale of Two Approaches": ["Probabilistic learning 2"], "Scalable Generative Models for Multi-label Learning with Missing Labels": ["Structured prediction"], "Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible": ["Privacy and security 2"], "Developing Bug-Free Machine Learning Systems With Formal Mathematics": ["ML and programming"], "The Statistical Recurrent Unit": ["Recurrent neural networks 2"], "Algebraic Variety Models for High-Rank Matrix Completion": ["Robust Estimation"], "Fast Bayesian Intensity Estimation for the Permanental Process": ["Bayesian Nonparametrics"], "Dropout Inference in Bayesian Neural Networks with Alpha-divergences": ["Deep learning 9: probabilistic"], "On the Expressive Power of Deep Neural Networks": ["Deep learning theory 3"], "Delta Networks for Optimized Recurrent Network Computation": ["Recurrent neural networks 1"], "Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery": ["Matrix factorization 2"], "Deep Spectral Clustering Learning": ["Metric learning"], "Fairness in Reinforcement Learning": ["Reinforcement learning 1"], "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks": ["Deep learning 3: metalearning"], "Measuring Sample Quality with Kernels": ["Probabilistic inference 2"], "Robust Probabilistic Modeling with Bayesian Data Reweighting": ["Probabilistic learning 1"], "Coordinated Multi-Agent Imitation Learning": ["Game theory and multiagents"], "Learning to Learn without Gradient Descent by Gradient Descent": ["Deep learning 4: learning to learn"], "Learning the Structure of Generative Models without Labeled Data": ["Probabilistic learning 3"], "Cost-Optimal Learning of Causal Graphs": ["Causal Inference 1"], "Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent Coarsening": ["Ranking and preferences"], "Consistency Analysis for Binary Classification Revisited": ["Learning theory 2"], "Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning": ["Deep reinforcement learning 1"], "Grammar Variational Autoencoder": ["Language 3"], "On Kernelized Multi-armed Bandits": ["Online learning 2"], "Forward and Reverse Gradient-Based Hyperparameter Optimization": ["Continuous optimization 6"], "Image-to-Markup Generation with Coarse-to-Fine Attention": ["Language 1"], "Learning Infinite Layer Networks without the Kernel Trick": ["Supervised learning 2"], "A Simulated Annealing Based Inexact Oracle for Wasserstein Loss Minimization": ["Monte Carlo methods 1"], "A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI": ["Probabilistic inference 2"], "Learning to Generate Long-term Future via Hierarchical Prediction": ["Recurrent neural networks 4"], "Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier": ["Healthcare"], "Deciding How to Decide: Dynamic Routing in Artificial Neural Networks": ["Deep reinforcement learning 2"], "Neural Optimizer Search using Reinforcement Learning": ["Deep reinforcement learning 2"], "Nearly Optimal Robust Matrix Completion": ["Matrix factorization 2"], "Learning Discrete Representations via Information Maximizing Self-Augmented Training": ["Infomation theory"], "Input Switched Affine Networks: An RNN Architecture Designed for Interpretability": ["Recurrent neural networks 2"], "Fake News Mitigation via Point Process Based Intervention": ["Reinforcement learning 2"], "Co-clustering through Optimal Transport": ["Clustering 2"], "Adaptive Consensus ADMM for Distributed Optimization": ["Distributed optimization"], "Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence": ["Continuous optimization 1"], "Curiosity-driven Exploration by Self-supervised Prediction": ["Reinforcement learning 3"], "Accelerating Eulerian Fluid Simulation With Convolutional Networks": ["Applications"], "Kernelized Support Tensor Machines": ["Supervised learning 1"], "Improving Viterbi is Hard: Better Runtimes Imply Faster Clique Algorithms": ["Probabilistic inference 1"], "Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study": ["Deep learning 7: analysis"], "Differentially Private Clustering in High-Dimensional Euclidean Spaces": ["Privacy and security 2"], "Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs": ["Structured prediction"], "Recurrent Highway Networks": ["Recurrent neural networks 1"], "Robust Budget Allocation via Continuous Submodular Functions": ["Combinatorial optimization 2"], "Faster Principal Component Regression and Stable Matrix Chebyshev Approximation": ["Spectral methods"], "Parallel Multiscale Autoregressive Density Estimation": ["Deep generative models 1"], "Breaking Locality Accelerates Block Gauss-Seidel": ["Continuous optimization 2"], "Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo": ["Deep generative models 3"], "Logarithmic Time One-Against-Some": ["Supervised learning 2"], "An Adaptive Test of Independence with Analytic Kernel Embeddings": ["Kernel methods"], "Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms": ["Continuous optimization 3"], "Multi-fidelity Bayesian Optimisation with Continuous Approximations": ["Bayesian Optimization"], "Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations": ["Matrix factorization 2"], "Leveraging Union of Subspace Structure to Improve Constrained Clustering": ["Active learning"], "An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation": ["Matrix factorization 3"], "Deep Bayesian Active Learning with Image Data": ["Probabilistic learning 2"], "Dance Dance Convolution": ["Applications"], "McGan: Mean and Covariance Feature Matching GAN": ["Deep generative models 2"], "Conditional Image Synthesis with Auxiliary Classifier GANs": ["Deep generative models 2"], "Active Heteroscedastic Regression": ["Active learning"], "Algorithms for $\\ell_p$ Low-Rank Approximation": ["Matrix factorization 3"], "Uniform Convergence Rates for Kernel Density Estimation": ["Learning theory 2"], "Bayesian Optimization with Tree-structured Dependencies": ["Bayesian Optimization"], "Deep Transfer Learning with Joint Adaptation Networks": ["Deep learning 3: metalearning"], "Lost Relatives of the Gumbel Trick": ["Probabilistic inference 3"], "Hierarchy Through Composition with Multitask LMDPs": ["Reinforcement learning 4"], "Risk Bounds for Transferring Representations With and Without Fine-Tuning": ["Transfer and multitask learning"], "Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks": ["Continuous optimization 3"], "Robust Structured Estimation with Single-Index Models": ["High dimensional estimation"], "Deep Tensor Convolution on Multicores": ["Deep learning 8: hardware"], "Variational Inference for Sparse and Undirected Models": ["Probabilistic inference 1"], "Unifying task specification in reinforcement learning": ["Reinforcement learning 4"], "Axiomatic Attribution for Deep Networks": ["Deep learning 7: analysis"], "PixelCNN Models with Auxiliary Variables for Natural Image Modeling": ["Deep generative models 1"], "Visualizing and Understanding Multilayer Perceptron Models: A Case Study in Speech Processing": ["Deep learning 7: analysis"], "Unimodal Probability Distributions for Deep Ordinal Classification": ["Deep learning 9: probabilistic"], "Density Level Set Estimation on Manifolds with DBSCAN": ["Learning theory 2"], "Guarantees for Greedy Maximization of Non-submodular Functions with Applications": ["Combinatorial optimization 1"], "ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning": ["Large scale learning"], "Exact Inference for Integer Latent-Variable Models": ["Probabilistic inference 1"], "Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis": ["Healthcare"], "Understanding Synthetic Gradients and Decoupled Neural Interfaces": ["Deep learning 1: backprop"], "Efficient Online Bandit Multiclass Learning with O(sqrt{T}) Regret": ["Online learning 4"], "Second-Order Kernel Online Convex Optimization with Adaptive Sketching": ["Online learning 2"], "Tensor Decomposition with Smoothness": ["Matrix factorization 2"], "DeepBach: a Steerable Model for Bach Chorales Generation": ["Recurrent neural networks 3"], "Convolutional Sequence to Sequence Learning": ["Language 3"], "Differentially Private Chi-squared Test by Unit Circle Mechanism": ["Privacy and security 2"], "Enumerating Distinct Decision Trees": ["Supervised learning 1"], "Large-Scale Evolution of Image Classifiers": ["Large scale learning"], "OptNet: Differentiable Optimization as a Layer in Neural Networks": ["Deep learning 6"], "Learning Continuous Semantic Representations of Symbolic Expressions": ["Language 2"], "Tensor Decomposition via Simultaneous Power Iteration": ["Matrix factorization 3"], "Count-Based Exploration with Neural Density Models": ["Deep reinforcement learning 1"], "Analytical Guarantees on Numerical Precision of Deep Neural Networks": ["Deep learning theory 2"], "Iterative Machine Teaching": ["Semisupervised and curriculum learning"], "Parseval Networks: Improving Robustness to Adversarial Examples": ["Deep learning 6"], "Decoupled Neural Interfaces using Synthetic Gradients": ["Deep learning 1: backprop"], "Self-Paced Co-training": ["Semisupervised and curriculum learning"], "SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling": ["Latent feature models"], "Combined Group and Exclusive Sparsity for Deep Neural Networks": ["Deep learning 5: Fisher approximations"], "Local-to-Global Bayesian Network Structure Learning": ["Probabilistic learning 3"], "On Calibration of Modern Neural Networks": ["Deep learning 7: analysis"], "Active Learning for Cost-Sensitive Classification": ["Active learning"], "Bidirectional learning for time-series models with hidden units": ["Time series"], "Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares": ["Continuous optimization 2"], "Reinforcement Learning with Deep Energy-Based Policies": ["Reinforcement learning 2"], "Optimal Densification for Fast and Accurate Minwise Hashing": ["Large scale learning"], "Learning Determinantal Point Processes with Moments and Cycles": ["Probabilistic learning 2"], "Sequence Tutor: Conservative fine-tuning of sequence generation models with KL-control": ["Recurrent neural networks 3"], "Deep Generative Models for Relational Data with Side Information": ["Networks and relational learning"], "Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for MCMC": ["Monte Carlo methods 1"], "Variational Dropout Sparsifies Deep Neural Networks": ["Deep learning 9: probabilistic"], "How to Escape Saddle Points Efficiently": ["Continuous optimization 7"], "Stochastic DCA for the Large-sum of Non-convex Functions Problem and its Application to Group Variable Selection in Classification": ["Continuous optimization 2"], "Dissipativity Theory for Nesterov's Accelerated Method": ["Continuous optimization 6"], "RobustFill: Neural Program Learning under Noisy I/O": ["ML and programming"], "Multichannel End-to-end Speech Recognition": ["Language 1"], "Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks": ["Deep generative models 1"], "Estimating individual treatment effect: generalization bounds and algorithms": ["Causal Inference 1"], "Online Partial Least Square Optimization: Dropping Convexity for Better Efficiency and Scalability": ["Latent feature models"], "Batched High-dimensional Bayesian Optimization via Structural Kernel Learning": ["Bayesian Nonparametrics"], "The loss surface of deep and wide neural networks": ["Deep learning theory 1"], "Diameter-Based Active Learning": ["Active learning"], "Wasserstein Generative Adversarial Networks": ["Deep generative models 2"], "Coresets for Vector Summarization with Applications to Network Graphs": ["Matrix factorization 1"], "Tensor-Train Recurrent Neural Networks for Video Classification": ["Recurrent neural networks 4"], "Automatic Discovery of the Statistical Types of Variables in a Dataset": ["Probabilistic learning 1"], "Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization": ["Continuous optimization 3"], "Regularising Non-linear Models Using Feature Side-information": ["Deep learning 6"], "Deletion-Robust Submodular Maximization: Data Summarization with \"the Right to be Forgotten\"": ["Combinatorial optimization 2"], "Innovation Pursuit: A New Approach to the Subspace Clustering Problem": ["Sparsity 2"], "Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP": ["Online learning 4"], "Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates": ["Matrix factorization 1"], "Video Pixel Networks": ["Deep generative models 1"], "Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks": ["Deep learning theory 1"], "Warped Convolutions: Efficient Invariance to Spatial Transformations": ["Deep learning 2: invariances"], "Learning Texture Manifolds with the Periodic Spatial GAN": ["Deep generative models 1"], "meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting": ["Deep learning 1: backprop"], "Joint Dimensionality Reduction and Metric Learning: A Geometric Take": ["Metric learning"], "High-dimensional Non-Gaussian Single Index Models via Thresholded Score Function Estimation": ["High dimensional estimation"], "Deep Voice: Real-time Neural Text-to-Speech": ["Recurrent neural networks 3"], "Bottleneck Conditional Density Estimation": ["Deep generative models 3"], "Interactive Learning from Policy-Dependent Human Feedback": ["Reinforcement learning 3"], "Stochastic modified equations and adaptive stochastic gradient algorithms": ["Continuous optimization 6"], "Data-Efficient Policy Evaluation Through Behavior Policy Search": ["Reinforcement learning 5"], "Graph-based Isometry Invariant Representation Learning": ["Deep learning 2: invariances"], "Capacity Releasing Diffusion for Speed and Locality.": ["Spectral methods"], "High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm": ["Robust Estimation"], "Lazifying Conditional Gradient Algorithms": ["Continuous optimization 5"], "Uncovering Causality from Multivariate Hawkes Integrated Cumulants": ["Causal Inference 1"], "Frame-based Data Factorizations": ["Matrix factorization 1"], "Asymmetric Tri-training for Unsupervised Domain Adaptation": ["Transfer and multitask learning"], "Depth-Width Tradeoffs in Approximating Natural Functions With Neural Networks": ["Deep learning theory 3"], "Partitioned Tensor Factorizations for Learning Mixed Membership Models": ["Matrix factorization 1"], "Priv\u2019IT: Private and Sample Efficient Identity Testing": ["Privacy and security 1"], "Identifying Best Interventions through Online Importance Sampling": ["Causal Inference 2"], "Minimax Regret Bounds for Reinforcement Learning": ["Reinforcement learning 1"], "Efficient Nonmyopic Active Search": ["Active learning"], "Why is Posterior Sampling Better than Optimism for Reinforcement Learning?": ["Reinforcement learning 1"], "Efficient Distributed Learning with Sparsity": ["Sparsity 2"], "Hyperplane Clustering Via Dual Principal Component Pursuit": ["Clustering 1"], "Magnetic Hamiltonian Monte Carlo": ["Monte Carlo methods 2"], "Prediction and Control with Temporal Segment Models": ["Reinforcement learning 2"], "Differentially Private Learning of Graphical Models using CGMs": ["Privacy and security 1"], "Learning Hierarchical Features from Deep Generative Models": ["Deep generative models 3"], "Differentially Private Ordinary Least Squares": ["Privacy and security 1"], "Active Learning for Accurate Estimation of Linear Models": ["Online learning 4"], "Stochastic Generative Hashing": ["Large scale learning"], "Clustering by Sum of Norms: Stochastic Incremental Algorithm, Convergence and Cluster Recovery": ["Clustering 2"], "Practical Gauss-Newton Optimisation for Deep Learning": ["Continuous optimization 4"], "Consistent On-Line Off-Policy Evaluation": ["Reinforcement learning 5"], "Multilevel Clustering via Wasserstein Means": ["Clustering 1"], "Multiplicative Normalizing Flows for Variational Bayesian Neural Networks": ["Deep learning 9: probabilistic"], "A Distributional Perspective on Reinforcement Learning": ["Reinforcement learning 4"], "Counterfactual Data-Fusion for Online Reinforcement Learners": ["Causal Inference 2"], "FeUdal Networks for Hierarchical Reinforcement Learning": ["Deep reinforcement learning 2"], "Clustering High Dimensional Dynamic Data Streams": ["Clustering 2"], "Stochastic Gradient Monomial Gamma Sampler": ["Monte Carlo methods 2"], "On Relaxing Determinism in Arithmetic Circuits": ["Probabilistic learning 3"], "Analysis and Optimization of Graph Decompositions by Lifted Multicuts": ["Combinatorial optimization 2"], "Modular Multitask Reinforcement Learning with Policy Sketches": ["Reinforcement learning 4"], "Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs": ["Networks and relational learning"], "Adaptive Sampling Probabilities for Non-Smooth Optimization": ["Continuous optimization 6"], "Latent LSTM Allocation: Joint clustering and non-linear dynamic modeling of sequence data": ["Recurrent neural networks 4"], "Fast k-Nearest Neighbour Search via Prioritized DCI": ["Metric learning"], "The Predictron:  End-To-End Learning and Planning": ["Deep reinforcement learning 1"], "Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders": ["Recurrent neural networks 3"], "The Price of Differential Privacy For Online Learning": ["Privacy and security 2"], "High Dimensional Bayesian Optimization with Elastic Gaussian Process": ["Gaussian processes"], "Probabilistic Path Hamiltonian Monte Carlo": ["Monte Carlo methods 2"], "Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs": ["Deep learning theory 3"], "On orthogonality and learning RNNs with long term dependencies": ["Recurrent neural networks 2"], "Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement": ["Combinatorial optimization 2"], "How Close Are the Eigenvectors of the Sample and Actual Covariance Matrices?": ["Spectral methods"], "Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables": ["Causal Inference 1"], "Stochastic Gradient MCMC Methods for Hidden Markov Models": ["Monte Carlo methods 2"], "Improving Gibbs Sampler Scan Quality with DoGS": ["Monte Carlo methods 1"], "Contextual Decision Processes with low Bellman rank are PAC-Learnable": ["Reinforcement learning 5"], "Sharp Minima Can Generalize For Deep Nets": ["Deep learning theory 1"], "Learning to Discover Sparse Graphical Models": ["Probabilistic learning 3"], "Analogical Inference for Multi-relational Embeddings": ["Networks and relational learning"], "Adaptive Neural Networks for Efficient Inference": ["Deep learning 5: Fisher approximations"], "Confident Multiple Choice Learning": ["Ensemble methods"], "Stochastic  Bouncy  Particle Sampler": ["Monte Carlo methods 1"], "Post-Inference Prior Swapping": ["Probabilistic learning 1"], "Equivariance Through Parameter-Sharing": ["Deep learning 2: invariances"], "A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates": ["Continuous optimization 3"], "A Unified View of Multi-Label Performance Measures": ["Structured prediction"], "Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction": ["Sparsity 2"], "Tensor Belief Propagation": ["Probabilistic inference 1"], "Dual Supervised Learning": ["Supervised learning 2"], "Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling": ["Language 1"], "Consistent k-Clustering": ["Clustering 1"], "Bayesian Boolean Matrix Factorisation": ["Probabilistic learning 2"], "Discovering Discrete Latent Topics with Neural Variational Inference": ["Language 2"], "Efficient softmax approximation for GPUs": ["Deep learning 8: hardware"], "Neural networks and rational functions": ["Learning theory 1"], "Oracle Complexity of Second-Order Methods for Finite-Sum Problems": ["Continuous optimization 1"], "Improved Variational Autoencoders for Text Modeling using Dilated Convolutions": ["Language 3"], "A Semismooth Newton Method for Fast, Generic Convex Programming": ["Continuous optimization 4"], "Constrained Policy Optimization": ["Reinforcement learning 2"], "Minimizing Trust Leaks for Robust Sybil Detection": ["Privacy and security 1"], "Tight Bounds for Approximate Carath\u00e9odory and Beyond": ["Continuous optimization 1"], "Multi-objective Bandits: Optimizing the Generalized Gini Index": ["Online learning 1"], "Soft-DTW: a Differentiable Loss Function for Time-Series": ["Time series"], "Projection-free Distributed Online Learning in Networks": ["Distributed optimization"], "Safety-Aware Algorithms for Adversarial Contextual Bandit": ["Online learning 3"], "World of Bits: An Open-Domain Platform for Web-Based Agents": ["Applications"], "Preferential Bayesian Optmization": ["Bayesian Optimization"], "Deep IV: A Flexible Approach for Counterfactual Prediction": ["Causal Inference 2"], "Provably Optimal Algorithms for Generalized Linear Contextual Bandits": ["Online learning 3"], "Algorithmic Stability and Hypothesis Complexity": ["Learning theory 2"], "Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use": ["Matrix factorization 3"], "Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks": ["Distributed optimization"], "Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank": ["Deep learning theory 2"], "Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis": ["Latent feature models"], "Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method": ["Semisupervised and curriculum learning"], "Gradient Boosted Decision Trees for High Dimensional Sparse Output": ["Ensemble methods"], "Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions": ["Continuous optimization 1"], "Attentive Recurrent Comparators": ["Recurrent neural networks 1"], "Conditional Accelerated Lazy Stochastic Gradient Descent": ["Continuous optimization 5"], "Neural Message Passing for Quantum Chemistry": ["Applications"], "Uniform Deviation Bounds for k-Means Clustering": ["Learning theory 2"], "Nystr\u00f6m Method with Kernel K-means++ Samples as Landmarks": ["Kernel methods"], "Learning Stable Stochastic Nonlinear Dynamical Systems": ["Continuous control"], "Model-Independent Online Learning for Influence Maximization": ["Online learning 1"], "Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values": ["Continuous optimization 4"], "Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data": ["Probabilistic learning 3"], "Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning": ["Deep reinforcement learning 1"], "On The Projection Operator to A Three-view Cardinality Constrained Set": ["Sparsity 1"], "Near-Optimal Design of Experiments via Regret Minimization": ["Combinatorial optimization 2"], "Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs": ["Recurrent neural networks 2"], "End-to-End Learning for Structured Prediction Energy Networks": ["Structured prediction"], "Globally Induced Forest: A Prepruning Compression Scheme": ["Ensemble methods"], "Identify the Nash Equilibrium in Static Games with Random Payoffs": ["Online learning 2"], "Neural Episodic Control": ["Deep reinforcement learning 2"]}, {"Greg Ongie": "University of Michigan", "Zhihua Zhang": "Peking University", "Hippolyt Ritter": "University College London", "Edwin Silverman": "Harvard Medical School", "Ken Kansky": "Vicarious AI", "Oriol Vinyals": "DeepMind", "Yingzhen Li": "University of Cambridge", "Inderjit Dhillon": "UT Austin & Amazon", "Dileep George": "Vicarious AI", "Changwei Hu": "Duke University", "Patrick F Riley": "Google", "Mengdi Wang": "Princeton University", "Honglak Lee": "Google / U. Michigan", "Aman Sinha": "Stanford University", "Sedat Ozer": "MIT", "Nicolas Vayatis": "ENS Cachan", "XIUYAN NI": "THE GRADUATE CENTER, CUNY", "Niao He": "UIUC", "Peter Frazier": "Cornell University", "Jason Pazis": "Amazon", "Liam Paninski": "", "David Pal": "Yahoo", "Kazuya Nakagawa": "Nagoya Institute of Technology", "Tengyuan Liang": "UPenn", "Motoaki Kawanabe": "ATR / RIKEN", "Yongguo Kang": "Baidu", "George Atia": "University of Central Florida", "Frans A Oliehoek": "University of Liverpool", "Victor-Emmanuel Brunel": "Massachusetts Institute of Technology", "Sreenivas Gollapudi": "", "Shunhua Jiang": "Tsinghua University", "Tom Schaul": "DeepMind", "Shinya Suzumura": "Nagoya Institute of Technology", "Alex Gittens": "Rensselaer Polytechnic Institute", "Robert Loftin": "North Carolina State University", "Puru Kar": "Indian Institute of Technology Kanpur", "Willie Neiswanger": "CMU", "Dan Klein": "UC Berkeley", "Elad Hazan": "Princeton University", "Bryant Chen": "IBM Research", "Mehrdad Farajtabar": "Georgia Tech", "Jean-Fran\u00e7ois Muzy": "Universit\u00e9 de Corse", "Eric Xing": "Carnegie Mellon University", "Kevin Scaman": "MSR-INRIA Joint Center", "wenwu zhu": "", "Matthew J Staib": "MIT", "Linlin Shen": "", "Xian Li": "Baidu", "James MacGlashan": "Cogitai", "Martin Takac": "Lehigh University", "Tao Sun": "University of Massachusetts Amherst", "Stephen Bach": "Stanford University", "Gaurav Sukhatme": "University of Southern California", "Jeff Schneider": "CMU/Uber", "Dhruv Mahajan": "Facebook", "Tomas Tunys": "Czech Technical University", "Martin Jaggi": "EPFL", "Youssef Mroueh": "IBM T.J Watson Research Center", "Alex Dimakis": "UT Austin", "Michael Kearns": "University of Pennsylvania", "Shayegan Omidshafiei": "MIT", "Denis Krompass": "Siemens AG", "Pang Wei Koh": "Stanford University", "Haoran Tang": "UC Berkeley", "Jianbo Ye": "Penn State University", "Marthinus C du Plessis": "N/A", "Aditi Raghunathan": "Stanford", "Zhe Li": "Syracuse University", "Guo-Jun Qi": "University of Central Florida", "Andrew McCallum": "UMass Amherst", "Andrei A Rusu": "DeepMind", "Hanbo Li": "UC San Diego", "Yueming LYU": "city university of hong kong", "Matt J. Kusner": "Alan Turing Institute", "Le Song": "Georgia Institute of Technology", "Hyunsoo Kim": "SK T-Brain", "Thomas D. Nielsen": "Aalborg University", "David L Roberts": "North Carolina State University", "Yingyu Liang": "Princeton University", "Will Dabney": "DeepMind", "Matt Taddy": "MICROSOFT", "Greg Valiant": "", "Shubho Sengupta": "Baidu Research", "Samy Bengio": "Google Brain", "Nick J Foti": "University of Washington", "Tie-Yan Liu": "Microsoft", "Olga Wichrowska": "Google Brain", "Geoff Converse": "Simpson College", "Bach Tran": "University of Lorraine", "Naresh Shanbhag": "University of Illinois", "Takaaki Hori": "MITSUBISHI ELECTRIC RESEARCH LABORATORIES", "John C Urschel": "Massachusetts Institute of Technology", "Lars Mescheder": "MPI T\u00fcbingen", "Lifang He": "University of Illinios at Chicago", "Rishabh Singh": "Microsoft Research", "Francis Bach": "INRIA", "Shubham Gupta": "Indian Institute of Science", "Elias Bareinboim": "Purdue", "Emmanuel Bengio": "McGill University", "Devansh Arpit": "", "Jun Sakuma": "University of Tsukuba / RIKEN AIP", "Shupeng Gui": "University of Rochester", "Chicheng Zhang": "UCSD", "Tom Sercu": "IBM Research", "Junier Oliva": "Carnegie Mellon University", "Chao Xu": "Peking University", "Michael Lyu": "The Chinese University of Hong Kong", "Noam Brown": "Carnegie Mellon University", "Yair Carmon": "Stanford University", "Jeff Dean": "Google Brain", "Ashia Wilson": "UC Berkeley", "Fran\u00e7ois Pachet": "Sony CSL / UPMC", "Angela Fan": "Facebook AI Research", "Ryan McKenna": "UMass Amherst", "Donald Goldfarb": "Columbia University", "Xi Chen": "New York University", "Stephan Mandt": "Disney Research", "J\u00fcrgen Schmidhuber": "Swiss AI Lab", "Ryohei Fujimaki": "-", "Mohammad Ghavamzadeh": "Adobe Research & INRIA", "Hiroyuki Nakahara": "RIKEN Brain Science Institute", "Shou-De Lin": "National Taiwan University", "Francesco Ald\u00e0": "Ruhr-Universit\u00e4t Bochum", "Li Jing": "Massachusetts Institute of Technology", "Shivaram Venkataraman": "UC Berkeley", "Pablo Sprechmann": "NYU", "Wenpeng Zhang": "Tsinghua University", "Peter Carr": "Disney Research", "Zoubin Ghahramani": "University of Cambridge & Uber", "Qi Meng": "Peking University", "Dixin Luo": "University of Toronto", "Jie Tan": "Google Inc.", "Prabhanjan Kambadur": "Bloomberg", "Rob Hyndman": "Monash University", "Mohammad Gheshlaghi Azar": "Deepmind", "Laurent Dinh": "University of Montreal", "Xi-Zhu Wu": "Nanjing University", "Yingbin Liang": "", "Issei Sato": "University of Tokyo / RIKEN", "Alexei Efros": "UC Berkeley", "Karthikeyan Shanmugam": "IBM Research, T. J. Watson Research Center", "Jamie Morgenstern": "University of Pennsylvania", "Robert Nowak": "University of Wisconsion-Madison", "Sebastian Scherer": "Carnegie Mellon University", "Svetha Venkatesh": "Deakin University", "Weihua Hu": "The University of Tokyo / RIKEN", "Roman Garnett": "Washington University in St. Louis", "Itai Caspi": "Technion", "Yacine Jernite": "New York University", "Shengjia Zhao": "Stanford University", "Ping Luo": "The Chinese University of Hong Kong", "Junhyuk Oh": "University of Michigan", "Chirag Gupta": "Microsoft Research, India", "Ichiro Takeuchi": "Nagoya Institute of Technology / RIKEN", "Minsik Cho": "IBM Research", "Adnan Darwiche": "UCLA", "David Woodruff": "", "Matt Bianchi": "Massachusetts General Hospital", "Erik Daxberger": "Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen", "Nathan Kallus": "Cornell University", "Yuan Zhou": "Indiana University Bloomington", "Pheng Ann Heng": "Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences", "Jiecao (Jack) Chen": "Indiana University Bloomington", "Dmitry Sorokin": "", "Jan Koutnik": "NNAISSENSE", "Changho Hwang": "KAIST", "Sayak Ray Chowdhury": "Indian Institute of Science", "David Gustafson": "University of Wisconsin-Madison", "Baharan Mirzasoleiman": "ETH Zurich", "Yeshwanth Cherapanamjeri": "Microsoft Research", "Serban A Stan": "Yale", "Peyton Greenside": "Stanford University", "Steven Hoi": "Singapore Management University", "John Duchi": "Stanford University", "Matthias Seeger": "Amazon.com", "Ai Kagawa": "Rutgers Univeristy", "Benjamin Recht": "Berkeley", "Qi Lei": "University of Texas at Austin", "Dino Oglic": "University of Bonn", "Elias Khalil": "Georgia Tech", "Claudio Gentile": "Universita dell'Insubria", "John Miller": "Baidu Research", "Siyu Liao": "", "Emily Fox": "University of Washington", "Ping Li": "Rugters University", "Chris Junchi Li": "Princeton University", "James Requeima": "University of Cambridge", "Zhengdong Lu": "DeeplyCurious.ai", "Christian Walder": "CSIRO Data61", "Marko Mitrovic": "Yale University", "Massimiliano Pontil": "University College London", "Riad Akrour": "TU Darmstadt", "Yusu Wang": "Ohio State University", "Jianshu Chen": "Microsoft Research", "Douglas Eck": "Google Brain", "Sercan Arik": "Baidu Research", "Xinghua Lou": "Vicarious AI", "Susan Murphy": "University of Michigan", "Sham Kakade": "University of Washington", "David Reichert": "DeepMind", "Lin Xiao": "Microsoft Research", "John Ingraham": "Harvard University", "Luca Franceschi": "IIT and UCL", "Yichen Chen": "Princeton University", "Ulf Brefeld": "Leuphana University", "Kai Zhong": "University of Texas at Austin", "Peter Liu": "Google Brain", "Eugene Belilovsky": "CentraleSupelec", "Moonsu Cha": "SK T-Brain", "Lam Nguyen": "Lehigh University", "Daniel Selsam": "Stanford University", "Ilija Bogunovic": "EPFL", "Yiming Yang": "Carnegie Mellon University", "Bishan Yang": "Carnegie Mellon University", "Sebastian Stich": "EPFL", "Ievgen Redko": "Universit\u00e9 Lyon 1 \u2013 INSA Lyon - Universit\u00e9 Jean Monnet Saint-Etienne.", "Satinder Singh": "University of Michigan", "He Zhao": "FIT, Monash University", "Jonas Kohler": "ETH Zurich", "Arthur Guez": "Google DeepMind", "Daniel Kane": "UCSD", "Daniel Carmon": "Tel-Aviv University", "David Belanger": "Google Brain", "Chris Donahue": "University of California, San Diego", "Alex Graves": "DeepMind", "Xiaojing Ye": "Georgia State University", "Judea Pearl": "UCLA", "Rodolphe Jenatton": "Amazon", "Gang Niu": "University of Tokyo", "James Zou": "Stanford", "Yinchong Yang": "Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Siemens AG", "Haim Avron": "Tel Aviv University", "Prateek Jain": "Microsoft Research", "Aditya Chaudhry": "University of Virginia", "Jinwoo Shin": "KAIST", "Sebastien Bubeck": "Microsoft Research", "Itay Safran": "Weizmann Institute of Science", "Scott Phoenix": "Vicarious AI", "Bjoern Andres": "MPI for Informatics", "Bryan Cai": "MIT", "Pulkit Agrawal": "", "Yuandong Tian": "Facebook AI Research", "Yunpeng Pan": "Georgia Tech", "Corinna Cortes": "Google Research", "Manzil Zaheer": "Carnegie Mellon University", "Andrew Ng": "Baidu", "Paolo Frasconi": "University of Florence", "Erik Sudderth": "University of California, Irvine", "Prof. Darrell": "University of California at Berkeley", "Geoff Pleiss": "Cornell University", "Matko Bo\u0161njak": "University College London", "Eric Price": "UT-Austin", "Wray Buntine": "Monash University", "Quanquan Gu": "University of Virginia", "Max Jaderberg": "DeepMind", "Alina Beygelzimer": "Yahoo Research", "Taifeng Wang": "", "Alessandro Lazaric": "FACEBOOK", "Bryan He": "Stanford University", "Yinyu Ye": "", "Abhimanu Kumar": "IMC Financial Markets", "Dar Gilboa": "Columbia University", "Odalric Maillard": "", "Yuanzhi Li": "Princeton University", "St\u00e9phane Ga\u00efffas": "CMAP CNRS UMR 7641", "Jonathan Tompson": "Google Brain", "Hal Daum\u00e9": "University of Maryland", "Lijun Zhang": "Nanjing University", "Jiaming Song": "Stanford University", "Klaus-robert Mueller": "", "Shuai Zheng": "Hong Kong University of Science and Technology", "Masrour Zoghi": "Independent Researcher", "Deepak Pathak": "UC Berkeley", "Hang Li": "Huawei", "Shahin Jabbari": "University of Pennsylvania", "Ashkan Panahi": "NC state university", "Wee Sun Lee Lee": "National University of Singapore", "Jacob Devlin": "Microsoft Research", "David L Dill": "Stanford University", "Sergei Vassilvitskii": "Google", "Kai Zheng": "Peking University", "Joseph Futoma": "Duke University", "Hung Bui": "Adobe Research", "Jim Fan Fan": "Stanford University", "Manolis Tsakiris": "Johns Hopkins University", "Saurabh Saxena": "Google Inc.", "Jiali Mei": "EDF R&D & Universit\u00e9 Paris-Sud", "Stefano Ermon": "Stanford University", "Hoai An Le Thi": "Theoretical and Applied Computer Science Laboratory, University of Lorraine", "Nico G\u00f6rnitz": "TU Berlin", "Qiqi Yan": "Google Inc.", "Matthew Hoffman": "DeepMind", "Nicholas Sidiropoulos": "University of Minnesota", "Wojciech Kotlowski": "Poznan University of Technology", "Joydeep Ghosh": "The University of Texas at Austin", "Wenbo Gao": "Columbia University", "Rina Panigrahy": "Google", "Philip Yu": "UIC", "Chelsea Finn": "UC Berkeley", "David Balduzzi": "Victoria University Wellington", "Ben Rubinstein": "University\u200b of Melbourne", "Chengtao Li": "MIT", "Piyush Rai": "IIT Kanpur", "Hao Zhou": "University of Wisconsin - Madison", "Peter Bartlett": "UC Berkeley", "Matteo Pirotta": "SequeL - Inria Lille - Nord Europe", "KyoungSoo Park": "KAIST", "Kai Fan": "", "Maurizio Filippone": "Eurecom", "Andre Barreto": "Google DeepMind", "Mason McGill": "California Institute of Technology", "Yongjune Kim": "UIUC", "Wilson Ye Chen": "University of Technology Sydney", "Pascal Frossard": "EPFL", "Dmitry Vetrov": "HSE", "Lezi Wang": "Rutgers", "Aditya Gopalan": "Indian Institute of Science", "Sanjay Shakkottai": "University of Texas at Austin", "Soumith Chintala": "Facebook", "Denis Yarats": "Facebook AI Research", "Teng Zhang": "Nanjing University", "Lerrel Pinto": "Carnegie Mellon University", "Rashish Tandon": "University of Texas at Austin", "Lancelot F. James": "Hong Kong University of Science and Technology", "Zhe Gan": "Duke University", "koray kavukcuoglu": "DeepMind", "Sandra Hirche": "Technical University of Munich", "Praneeth Netrapalli": "Microsoft Research", "Tolga Bolukbasi": "Boston University", "Richard Zemel": "University of Toronto", "Ashish Bora": "University of Texas at Austin", "Steve Young J Young": "University of Cambridge", "Yookoon Park": "Seoul National University", "L\u00e9on Bottou": "Facebook", "Sergio G\u00f3mez Colmenarejo": "Google DeepMind", "Sergey Levine": "Berkeley", "Marc Bellemare": "DeepMind", "Borja de Balle Pigem": "Amazon Research Cambridge", "Josiah Hanna": "University of Texas at Austin", "Rongda Zhu": "Facebook", "Sayan Mukherjee": "Duke University", "Or Sheffet": "University of Alberta", "Robert Bamler": "Disney Research Pittsburgh", "Liwei Wang": "Peking University", "Debora Marks": "Harvard Medical School", "Anant Raj": "Max-Planck Institute for Intelligent Systems", "Rebecca Willett": "UW Madison", "Kazuya Kakizaki": "University of Tsukuba / NEC", "Ke Li": "UC Berkeley", "Alessandro Sordoni": "Microsoft Maluuba", "M van der Schaar": "Oxford University and UCLA", "Po-Wei Chou": "Carnegie Mellon University", "Christopher Re": "Stanford", "Bo Yuan": "City College of New York, CUNY", "Shuguang Hu": "University of Hong Kong", "Anna Choromanska": "New York University", "Xixian Chen": "The Chinese University of Hong Kong", "Brian McWilliams": "Disney Research", "Gregory Valiant": "Stanford University", "Hongwei Liu": "Xidian University", "Jose Moura": "CMU", "Daniel Neil": "Institute of Neuroinformatics", "Shuang Li": "", "Neil Lawrence": "Amazon.com", "Konstantina Palla": "Oxford University", "Julian Zilly": "ETH Zurich", "Igor Mordatch": "OpenAI", "Seiya Tokui": "Preferred Networks / The University of Tokyo", "Abdelrahman Mohammad": "Microsoft", "Robert Busa-Fekete": "Yahoo! Research", "Sterling Johnson": "UW Madison", "Jungkwon Lee": "SK T-Brain", "Kshitij Fadnis": "IBM", "Qingshan Liu": "", "Rene Vidal": "Johns Hopkins University", "Wengong Jin": "MIT Computer Science and Artificial Intelligence Laboratory", "Bei Peng": "Washington State University", "Marc Law": "University of Toronto", "Matteo Hessel": "Deep Mind", "Nir Shavit": "MIT", "PENGFEI WEI": "Nanyang Technological University, Singapore", "Zi Wang": "MIT", "Krzysztof Dembczynski": "Poznan University of Technology", "Cyril Zhang": "Princeton University", "Mingmin Zhao": "MIT", "Christoph Studer": "Cornell University", "Christian Kroer": "Carnegie Mellon University", "James Kwok": "Hong Kong University of Science and Technology", "Asja Fischer": "Computer Science Department, University of Bonn", "Daniel McNamara": "Australian National University and Data61", "Marc Brockschmidt": "Microsoft Research", "Chenzi Zhang": "HKU", "Harry Lang": "Johns Hopkins University", "Sanjeev Satheesh": "Baidu SVAIL", "Bhargavi Paranjape": "Microsoft Research", "Alexander J Ratner": "Stanford University", "Lin Yang": "Johns Hopkins", "Sander Dieleman": "DeepMind", "Mario Lucic": "ETH Zurich", "Pan Xu": "University of Virginia", "Miltos Allamanis": "Microsoft Research", "Mohammad Shoeybi": "Baidu Research", "Mathieu Salzmann": "EPFL", "Peter Castaldi": "Harvard Medical School", "Dongdong Ge": "Shanghai University of Finance and Economics", "Patrick Thiran": "EPFL", "RAJIV KHANNA": "UT Austin", "Chi-Jen Lu": "Academia Sinica", "Scott Niekum": "University of Texas at Austin", "Michalis Titsias": "Athens University of Economics and Business", "Deepayan Chakrabarti": "University of Texas, Austin", "Bin Hong": "Zhejiang University", "Liping Liu": "Columbia University", "Carlos Villacampa-Calvo": "Universidad Aut\u00f3noma de Madrid", "CHI GOH": "", "Daniel Sheldon": "University of Massachusetts Amherst", "Shali Jiang": "Washington University in St. Louis", "Erick Matsen": "Fred Hutchinson Cancer Center", "Adrian Vladu": "MIT", "Rakshit Trivedi": "Georgia Institute of Technology", "Shashanka Ubaru": "University of Minnesota", "Javier Gonz\u00e1lez": "Amazon", "Pushmeet Kohli": "Microsoft Research", "Vaibhava Goel": "IBM", "Chao Chen": "City University of New York (CUNY)", "Mikhail Yurochkin": "University of Michigan", "alan Aspuru-Guzik": "", "Irwin King": "CUHK", "Shichao Yue": "MIT", "Li Deng": "Citadel", "David Barber": "University College London", "Yale Chang": "Northeastern University", "Gautam Dasarathy": "Rice University", "pankajan Chanthirasegaran": "", "Shixiang Gu": "Cambridge", "Yiping Ke": "Nanyang Technological University", "Anelia Angelova": "Google Brain", "Marcus Frean": "Victoria University Wellington", "Christopher Olah": "Google Brain", "Tobi Delbruck": "Institute of Neuroinformatics", "Jiang Bian": "Microsoft Research", "Amir Globerson": "Tel Aviv University", "Jean-Michel Begon": "University of Liege", "Jie Liu": "Lehigh University", "Ce Zhang": "ETH Zurich", "Mark Schmidt": "University of British Columbia", "Weizhong Zhang": "Zhejiang University & Tencent AI Lab", "Jun Zhu": "Tsinghua University", "Xu SUN": "Peking University", "Kannan Ramchandran": "UC Berkeley", "Mark Girolami": "Imperial College London", "Ajil Jalal": "University of Texas at Austin", "Ruiqi Guo": "Google Research", "Surya Ganguli": "Stanford", "Massil Achab": "Ecole Polytechnique", "Lubomir Bourdev": "WaveOne, Inc.", "Yunhe Wang": "Peking University", "Duy Nhat Phan": "Universite de Lorraine", "Isabel Valera": "University of Cambridge", "Zhi Chen": "Nanjing University", "Quoc Le": "Google Brain", "John Hershey": "MITSUBISHI ELECTRIC RESEARCH LABORATORIES", "Alexander Kolesnikov": "IST Austria", "Alan Qi": "Ant Financial", "Wittawat Jitkrittum": "UCL", "Chen Yu": "Indiana University", "Adrian Weller": "University of Cambridge", "Clayton T. Morrison": "University of Arizona", "Sanjay Hariharan": "Duke University", "Jason Hartford": "University of British Columbia", "Flavio Chierichetti": "Sapienza University of Rome", "Debora Sujono": "University of Massachusetts Amherst", "Yichen Shen": "MIT", "Volker Tresp": "University of Munich", "Cem Aksoylar": "", "Edward Pyzer-Knapp": "IBM", "Wei-Cheng Lee": "National Taiwan University", "Adam Roberts": "Google Brain", "Christopher Pal": "MILA", "Tuomas Haarnoja": "UC Berkeley", "Mostafa Rahmani": "University of Central Florida", "Esteban Real": "Google Inc.", "Yi-An Ma": "University of Washington", "Alexander Matveev": "MIT", "Philip Bachman": "Maluuba", "Erik Lindgren": "University of Texas at Austin", "Amina Mollaysa": "University of Geneva, HES", "Surya Bhupatiraju": "MIT", "Sammie Katt": "Northeastern University", "Shinichi Nakajima": "TU Berlin", "Kavosh Asadi": "Brown University", "Eugene Vorontsov": "MILA", "Huan Xu": "Georgia Tech", "Mario Figueiredo": "Instituto Superior Tecnico", "Sahand Negahban": "YALE", "Jon Shlens": "Google Brain", "Joachim Buhmann": "", "Tim Shi": "Stanford University", "Szymon Sidor": "OpenAI", "Nahum Shimkin": "Technion", "Vu Dinh": "Fred Hutchinson Cancer Center", "Jiachen Yang": "Georgia Institute of Technology", "Cho-Jui Hsieh": "University of California, Davis", "Arya Mazumdar": "University of Massachusetts Amherst", "Yaoliang Yu": "University of Waterloo", "Shih-Chii Liu": "Institute of Neuroinformatics", "Jie Wang": "University of Michigan", "Huan Zhang": "UC Davis", "Helge Langseth": "Norwegian University of Science and Technology", "Ashish Kapoor": "Microsoft Research", "Michael L. Littman": "Brown University", "Mathieu Blondel": "NTT", "Ryan Adams": "Google Brain and Princeton University", "Sebastian Riedel": "UCL", "Mark Bun": "Princeton University", "Chiheb Trabelsi": "Ecole Polytechnique de Montreal", "Bo Dai": "Georgia Tech", "Lingxiao Wang": "University of Virginia", "Jim Rehg": "Georgia Tech", "Jan Chorowski": "Google Brain", "Juyong Kim": "Seoul National University", "Qunwei Li": "Syracuse University", "Michael Jordan": "UC Berkeley", "Daan Wierstra": "Google DeepMind", "Rasmus Larsen": "Google", "David Gifford": "MIT", "Scott Yang": "Courant Institute", "David Knowles": "Stanford", "Steve Oudot": "", "Ofer Dekel": "Microsoft", "Sam Wong": "UC Berkeley", "Zhiting Hu": "Carnegie Mellon University", "Fredrik D Johansson": "MIT", "Gavin Taylor": "US Naval Academy", "Martin Wainwright": "University of California at Berkeley", "George Dahl": "Google Brain", "Michael Hay": "Colgate University", "Alex Smola": "Amazon", "Anastasia Pentina": "IST Austria", "Mohsen Ahmadi Fahandar": "Paderborn University", "Ming Gu": "University of California at Berkeley", "Paul Weng": "SYSU-CMU JIE", "Arthur Choi": "UCLA", "Ian Osband": "Deepmind", "Alnur Ali": "Carnegie Mellon University", "Yevgen Chebotar": "University of Southern California", "Steve Yadlowsky": "Stanford University", "Jennifer G Dy": "Northeastern University", "Nenghai Yu": "USTC", "Andrew Saxe": "Harvard University", "Chun-Ta Lu": "University of Illinois at Chicago", "Olivier Bachem": "ETH Zurich", "Tzu-Kuo Huang": "Uber", "Raghavendra Udupa": "Microsoft Research", "Yuchen Zhang": "Stanford", "Oren Rippel": "WaveOne, Inc.", "Dan Alistarh": "IST Austria & ETH Zurich", "Justin Gilmer": "Google Brain", "Shuxin Zheng": "University of Science and Technology of China", "Heinrich Jiang": "Google", "Chao-Yuan Wu": "UT Austin", "Pierre Geurts": "University of Liege", "Tim Rockt\u00e4schel": "University of Oxford", "Weiyang Liu": "Georgia Tech", "David Silver": "Google DeepMind", "Laura Balzano": "University of Michigan", "ARUN SUGGALA": "Carnegie Mellon University", "Yingce Xia": "University of Science and Technology of China", "Nilesh Tripuraneni": "UC Berkeley", "David Grangier": "Facebook", "Jonathan Eckstein": "Rutgers University", "Nirbhay Modhe": "Indian Institute of Technology Kanpur", "Jacob Menick": "DeepMind", "Ahmed M. Alaa Ibrahim": "UCLA", "Yin Tat Lee": "Microsoft Research", "Yohann De Castro": "LMO", "Tsendsuren Munkhdalai": "University of Massachusetts", "Lester Mackey": "Microsoft Research", "Mingyi Hong": "Iowa State University", "Rui Shu": "Stanford University", "Qi Xie": "", "Yannig Goude": "EDF Lab Paris-Saclay", "Zhihao Gavin Tang": "University of Hong Kong", "Gustavo Malkomes": "Washington University in St. Louis", "JesseEngel Engel": "Google Brain", "Jian Tang": "Syracuse University", "Katya Scheinberg": "Lehigh University", "Arka Pal": "DeepMind", "Friedemann Zenke": "Stanford", "Viet Huynh": "Deakin University", "C\u00e9dric Malherbe": "ENS Paris-Saclay", "Santu Rana": "Deakin University", "Zheng Wen": "Adobe Research", "Creighton Heaukulani": "Cambridge University", "Ke Sun": "KAUST", "Lili Mou": "Peking University", "Pradeep Ravikumar": "Carnegie Mellon University", "Deyu Meng": "", "Xiaotong Yuan": "Nanjing University of Information Science & Technology", "Alistair Stewart": "USC", "Martha White": "University of Alberta/Indiana University", "Abhinav Gupta": "Carnegie Mellon University", "Alexander Moreno": "Georgia Institute of Technology", "Jonathan Raiman": "Baidu Research", "Zohar Karnin": "yahoo", "Moein Falahatgar": "UCSD", "Arun Suggala": "Carnegie Mellon University", "Adam Trischler": "Maluuba", "Marco Cuturi": "ENSAE / CREST", "Evans Etrue Howard": "University of Insubria", "Renata Khasanova": "Ecole Polytechnique Federale de Lausanne (EPFL)", "Christopher Musco": "", "Alyssa Shofner": "University of South Carolina", "Jitendra Malik": "", "James Davidson": "Google Brain", "Gunhee Kim": "Seoul National University", "Jakob Foerster": "University of Oxford", "Benigno Uria": "Deepmind", "Mike Chrzanowski": "Baidu Research", "Philip Blunsom": "Oxford University and DeepMind", "David Budden": "MIT / DeepMind", "Richard I Hartley": "Australian National University", "Wan-Duo Ma": "Victoria University of Wellington", "Constantinos Daskalakis": "MIT", "Sebastian Nowozin": "Microsoft Research", "Jie Shen": "Rutgers University", "Kohei Hayashi": "AIST / RIKEN", "Grace Wahba": "University of Wisconsin-Madison", "Taeksoo Kim": "SK T-Brain", "Thomas Gaertner": "The University of Nottingham", "Azalia Mirhoseini": "Google", "Jerry Li": "MIT", "Soheil Mohajer": "University of Minnesota", "Jonas Umlauft": "Technical University of Munich", "Sebastian Tschiatschek": "ETH", "Greg Farquhar": "University of Oxford", "Arman Bilge": "University of Washington", "Basarab Matei": "", "Zichao Yang": "Carnegie Mellon University", "Li Shen": "Tencent", "Yutian Chen": "DeepMind", "Eyke H\u00fcllermeier": "Paderborn University", "Avinatan Hassidim": "Bar Ilan University", "Gygli Gygli": "Gifs.com", "Xuanyi Dong": "University of Technology Sydney", "Yuefeng Zhou": "Google Brain", "Yangchen Pan": "Indiana University", "Tatsuya Harada": "The Univ. of Tokyo / RIKEN", "Regina Barzilay": "MIT CSAIL", "Andreas Geiger": "MPI T\u00fcbingen", "Ahmad Humayun": "Georgia Institute of Technology", "Sebastian Mair": "Leuphana University L\u00fcneburg", "Jeffrey Pennington": "Google Brain", "agibiansky Gibiansky": "Baidu Research Silicon Valley AI Lab", "Ian Yen": "Carnegie Mellon University", "Travis Dick": "CMU", "Youn\u00e8s Bennani": "", "Francois-Xavier Briol": "University of Warwick", "Xiaodan Liang": "Carnegie Mellon University", "Nate Kushman": "Microsoft Research", "Ken Perlin": "New York University", "Kurt Cutajar": "EURECOM", "Yuntian Deng": "Harvard University", "Byron Boots": "Georgia Tech", "David GT Barrett": "DeepMind", "Yixin Wang": "Columbia University", "Arthur Gretton": "Gatsby Computational Neuroscience Unit", "Tong Zhang": "Tecent AI Lab", "Sherry Moore": "Google Inc.", "Alexander Bauer": "TU Berlin", "Pietro Michiardi": "EURECOM", "Yu Sun": "Cornell University", "Daniel Maturana": "Carnegie Mellon University", "Dario Ramos-Lopez": "University of Almeria", "Miroslav Dudik": "Microsoft Research", "Jon Cockayne": "University of Warwick", "Riashat Islam": "McGill University", "Antonio Salmeron": "University of Almeria", "James Bailey": "The University of Melbourne", "Sanjeev Arora": "Princeton University", "James Wang": "Penn State University", "Anshumali Shrivastava": "Rice University", "Sam Ritter": "DeepMind", "Zhiming Ma": "", "Ramon Sagarna": "", "Marlos C. Machado": "University of Alberta", "Nimrod Dorfman": "Vicarious AI", "Di Lin": "Shenzhen University", "Mehryar Mohri": "Courant Institute and Google Research", "Balazs Szorenyi": "Technion", "Adrian N Bishop": "Data61/ANU/UTS", "Martin Arjovsky": "New York University", "Yichi Zhou": "Tsinghua University", "David Krueger": "MILA", "Matthew Joseph": "University of Pennsylvania", "Nantas Nardelli": "University of Oxford", "Hao Yin": "Stanford University", "Siamak Ravanbakhsh": "Carnegie Mellon University", "Zheng Xu": "University of Maryland", "Urs M Bergmann": "Zalando Research", "Ankur Taly": "Google Inc.", "Max Welling": "University of Amsterdam", "Lan Du": "Faculty of Information Technology, Monash University", "Guillaume Gautier": "INRIA Lille", "Haishan Ye": "Shanghai Jiao Tong University", "Michele Donini": "IIT", "Insu Han": "Korea Advanced Institute of Science and Technology", "Bo Liu": "Rutgers", "Georg Ostrovski": "Google DeepMind", "Anders Madsen": "Hugin Expert A/S", "Chaoxu Zhou": "Columbia University", "Drew Bagnell": "Carnegie Mellon University", "Andrew Hellicar": "CSIRO", "Pedram Pad": "Ecole Polytechnique Federale de Lausanne (EPFL)", "Dacheng Tao": "", "Edwin Bonilla": "UNSW", "Tao Lei": "MIT CSAIL", "Karol Hausman": "University of Southern California", "Yuliang Zou": "University of Michigan", "Chris Scott": "Chestnut Health Systems", "Andrew Forney": "UCLA", "Armand Joulin": "Facebook", "Charles Blundell": "DeepMind", "Nan Jiang": "Microsoft Research", "Carlo D'Eramo": "Politecnico di Milano", "Tony Butler-Yeoman": "Victoria University of Wellington", "David A M\u00e9ly": "Vicarious AI", "Pranav Shyam": "R. V. College of Engineering & Indian Institute of Science", "David Sontag": "Massachusetts Institute of Technology", "Wei Chen": "Microsoft Research", "Michael Unser": "", "Benjamin Rosman": "Council for Scientific and Industrial Research (CSIR)", "Long Nguyen": "University of Michigan", "Hirakendu Das": "Yahoo!", "Dave Anderson": "UC Berkeley", "Arnaud Joly": "University of Liege", "John E Peurifoy": "MIT", "Joe Wang": "Amazon", "Sriram Vishwanath": "", "Mladen Kolar": "University of Chicago", "Michael Kapralov": "EPFL", "Hongyang Zhang": "Carnegie Mellon University", "Samuele Tosatto": "Politecnico di Milano", "Andreas Krause": "ETH Zurich", "Michael Bowling": "University of Alberta", "Mingyuan Zhou": "University of Texas at Austin", "Dan Feldman": "", "Zhi-Hua Zhou": "Nanjing University", "Cedric Archambeau": "Amazon", "Grady Williams": "Georgia Tech", "J.P. Lewis": "Frostbite Labs and Victoria University", "Naveen Kumar": "Google", "Michael Cho": "Harvard Medical School", "Kilian Weinberger": "Cornell University", "Wei Liu": "Tencent AI Lab", "Razvan Pascanu": "DeepMind", "Karan Singh": "Princeton University", "Pieter Abbeel": "OpenAI / UC Berkeley", "Miguel Lazaro-Gredilla": "Vicarious AI", "Chong Wang": "Microsoft Research", "Jascha Sohl-Dickstein": "Google Brain", "Tyler Johnson": "University of Washington", "Anshul Kundaje": "Stanford University", "Xunyu Lin": "", "Jialian Li": "Tsinghua University", "Sung-En Chang": "National Taiwan University", "Vatsal Sharan": "Stanford University", "Matej Balog": "University of Cambridge", "Po-Sen Huang": "Microsoft Research", "Tao Qin": "Microsoft Research Asia", "ROI Livni": "Princeton", "Felix Xinnan Yu": "Google Research", "Frank Nielsen": "Sony CSL, Japan", "NIKOS KARAMPATZIAKIS": "Microsoft", "Andrew Miller": "Harvard", "Volkan Cevher": "EPFL", "Nan Ye": "Queensland University of Technology", "Changho Suh": "KAIST", "Thomas Degris": "DeepMind", "Alexandros Kalousis": "HES-UNIGE", "Guanghui ": "George", "Christopher Burgess": "DeepMind", "Zoltan Szabo": "\u00c9cole Polytechnique", "Laurent Lessard": "University of Wisconsin-Madison", "Kristofer D Schlachter": "New York University", "Nima Mesgarani": "Columbia University", "Morteza Zadimoghaddam": "Google", "Jun Lee": "Samsung Advanced Institute of Technology", "Yizhe Zhang": "Duke university", "Avanti Shrikumar": "Stanford University", "Margo Seltzer": "Harvard University", "Fan Ma": "Xian Jiaotong University", "Aaron Courville": "University of Montreal", "Kevin Leyton-Brown": "", "Peter Stone": "University of Texas at Austin", "Zilong Tan": "Duke University", "Yi Zhang": "Princeton University", "Ivo Danihelka": "Google DeepMind", "Matthias Hein": "Saarland University", "Kyoungsoo Park": "KAIST", "Davood Hajinezhad": "Iowa State University", "Nicolas Heess": "Google DeepMind", "Marin Solja\\v{c}i\\'{c}": "MIT", "Aaron Sidford": "Stanford", "Hoang M Le": "Caltech", "Jose Hernandez-Lobato": "University of Cambridge", "Shibani Santurkar": "MIT", "Adam Coates": "Baidu SVAIL", "Umut Simsekli": "Telecom ParisTech", "Zhuoran Yang": "Princeton University", "Neil Rabinowitz": "DeepMind", "Salvatore Ruggieri": "Universit\u00e0 di Pisa", "Shaked Shammah": "Hebrew University, Jerusalem", "Sunil Gupta": "Deakin University", "Seungjin Choi": "POSTECH", "Yi Zhou": "Syracuse University", "Kaan Kara": "ETH Zurich", "Matus Telgarsky": "UIUC", "Anssi Kanervisto": "University of Eastern Finland", "Vincent Brault": "Univ. Grenoble Alpes", "Yu Lu": "Yale University", "Sharan Vaswani": "University of British Columbia", "G\u00e1bor Braun": "", "Farnood Salehi": "EPFL", "Hubert Chan": "University of Hong Kong", "Mohammad Golbabaee": "the University of Edinburgh", "Philippe Rigollet": "MIT", "Satwik Kottur": "Carnegie Mellon University", "Tammo Rukat": "University of Oxford", "Alex Botev": "University College London", "Scott B Hu": "UCLA", "Chiranjib Bhattacharya": "", "Alexandros Karatzoglou": "Telefonica Research", "Dinghan Shen": "Duke University", "Jonathan Scarlett": "EPFL", "Daniel Brand": "IBM Research", "Adam Klivans": "University of Texas at Austin", "Pietro Perona": "caltech.edu", "Yichen Wang": "Gatech", "Tasha Nagamine": "Columbia University", "Philip S. Thomas": "CMU", "Ricardo Henao": "Duke University", "Roland Vollgraf": "Zalando Research", "Mo Eldawy": "Vicarious AI", "Vikas Singh": "", "Loic Matthey": "DeepMind", "Shuming Ma": "Peking University", "Arsenii Ashukha": "HSE, MIPT", "Qin Zhang": "Indiana University Bloomington", "Peilin Zhao": "Artificial Intelligence Department, Ant \u200bFinancial", "Percy Liang": "Stanford University", "Dan Belov": "Google", "Nicolas Ballas": "Universit\u00e9 de Montr\u00e9al", "Maithra Raghu": "Google Brain / Cornell University", "Jiwon Kim": "SK T-Brain", "Yulai Cong": "Xidian University", "Xiao Fu": "University of Minnesota", "Kartik Gupta": "Microsoft Research", "Changyou Chen": "Duke", "Andreas Loukas": "EPFL", "Andreas B\u00e4rmann": "FAU Erlangen-N\u00fcrnberg", "Zakaria mhammedi": "The University of Melbourne", "Guangyong Chen": "The Chinese University of Hong Kong", "Luo Luo": "Shanghai Jiao Tong University", "Yasaman Bahri": "Google Brain", "Matt Grossglauser": "EPFL", "Rong Ge": "Duke University", "Yuta Umezu": "Nagoya Institute of Technology", "Laks V.S Lakshmanan": "University of British Columbia", "Jeffrey Ling": "Harvard University", "Venkatadheeraj Pichapati": "University of California San Diego", "John L Vian": "The Boeing Company", "Akshay Krishnamurthy": "UMass", "Jialei Wang": "University of Chicago", "Chuan Guo": "Cornell University", "Phil Torr": "Oxford", "Triantafyllos Afouras": "University of Oxford", "Jia Li": "Penn State University", "Si Si": "Google Research", "Jan-Hendrik Lange": "MPI for Informatics", "Gerome Miklau": "University of Massachusetts, Amherst", "Christopher Beckham": "MILA", "Aviv Tamar": "UC Berkeley", "Tommi Jaakkola": "MIT", "Tengyu Ma": "Princeton University", "Taro Sekiyama": "IBM Research - Tokyo", "Yisong Yue": "Caltech", "Koji Tsuda": "University of Tokyo / RIKEN", "Patrick Lucey": "STATS", "Ziyu Wang": "Deep Mind", "Michael C. Hughes": "Harvard University", "Daniela Rus": "", "Michael Dennis": "Lighthouse Institute", "Stefanie Jegelka": "MIT", "Barret Zoph": "Google", "Lawrence Carin": "Duke", "Ilias Diakonikolas": "USC", "Jan Peters": "TU Darmstadt", "Hao Hu": "University of Central Florida", "Jon Kleinberg": "Cornell University", "Bangrui Chen": "Cornell University", "Edouard Grave": "Facebook AI Research", "Kyle Kastner": "", "Nikolay Jetchev": "Zalando Research", "Xueyu Mao": "University of Texas at Austin", "Yossi Arjevani": "Weizmann Institute of Science", "Karen Simonyan": "DeepMind", "Lior Wolf": "Facebook AI Research and Tel Aviv University", "Han Liu": "Princeton University", "Shandian Zhe": "Purdue University", "Yilin Zhang": "", "Liran Szlak": "Weizmann Institute of Science", "Nando de Freitas": "DeepMind", "Sanjoy Dasgupta": "UCSD", "Niru Maheswaranathan": "Stanford University", "Paul Mineiro": "Microsoft", "Jonas Mueller": "MIT", "Ankit Goyal": "University of Michigan", "R\u00e9mi Bardenet": "CNRS and Univ. Lille", "Colin Dawson": "Oberlin College", "Stefan Schaal": "", "Dzmitry Bahdanau": "Universit\u00e9 de Montr\u00e9al", "Gabriele Farina": "Carnegie Mellon University", "Zizhuo Wang": "University of Minnesota", "Vladimir Braverman": "Johns Hopkins University", "Shen Wang": "University of Illinios at Chicago", "Scott Skirlo": "MIT", "Mohammad Norouzi": "Google", "Natasha Jaques": "Massachusetts Institute of Technology", "James Taylor": "University of Oxford", "Garrett Bernstein": "University of Massachusetts Amherst", "Jason Naradowsky": "University of Cambridge", "Yarin Gal": "University of Cambridge", "Qihang Lin": "Univ Iowa", "Samuel Kadoury": "Ecole Polytechnique de Montreal", "Reinhard Heckel": "UC Berkeley", "G\u00e1bor Lugosi": "Universitat Pompeu Fabra", "Ravi Kumar": "Google", "Takayuki Osogami": "IBM Research - Tokyo", "Shengyu Zhang": "CUHK", "Vikas Jain": "Indian Institute of Technology Kanpur", "Purnamrita Sarkar": "UT Austin", "Joao Henriques": "University of Oxford", "Jonas Gehring": "Facebook AI Research", "Dimitris Metaxas": "Rutgers", "Nagarajan Natarajan": "Microsoft Research", "Nati Srebro": "Toyota Technological Institute at Chicago", "Ashish Kumar": "Microsoft Research", "Max Tegmark": "MIT", "Aaron Roth": "University of Pennsylvania", "Kazuto Fukuchi": "University of Tsukuba", "Ankur Moitra": "", "Hao Peng": "Purdue University", "Demis Hassabis": "Deepmind", "Daniele Calandriello": "INRIA Lille", "Ben Poole": "Stanford University", "Aapo Hyv\u00e4rinen": "UCL", "Tim Lillicrap": "Google DeepMind", "Amir Zandieh": "EPFL", "Lei Xu": "Carnegie Mellon University", "Jonathan Hernandez": "", "Emmanuel Bacry": "Ecole Polytechnique", "Hado van Hasselt": "DeepMind", "Cinjon Resnick": "Google Brain", "Ron Weiss": "Google Brain", "Takeru Miyato": "Preferred Networks, Inc., ATR", "Juho Lee": "POSTECH", "Silvio Lattanzi": "Google Zurich", "Jacob Andreas": "UC Berkeley", "Arturs Backurs": "MIT", "Rajat Sen": "University of Texas at Austin", "Andrea Vedaldi": "University of Oxford", "Xiaofei He": "Zhejiang University", "Irwan Bello": "Google Brain", "Sasha Vezhnevets": "DeepMind", "Xiangang Li": "Baidu AI Lab", "Yining Wang": "CMU", "Taylor Berg-Kirkpatrick": "", "Cynthia Rudin": "Duke University", "Greg Lewis": "Microsoft Research", "Boba Mitrovic": "EPFL", "Jimei Yang": "Adobe Research", "Vamsi Ithapu": "Univresity of Wisconsin Madiso", "Carlos Guestrin": "", "jaehong yoon": "UNIST", "benoit steiner": "Google", "Aarti Singh": "Carnegie Mellon University", "Gerhard Neumann": "University of Lincoln", "Chengxiang Zhai": "University of Illinois at Urbana-Champaign", "Nikhil Mishra": "UC Berkeley", "kirthevasan kandasamy": "CMU", "Daniel Stefankovic": "University of Rochester", "Marvin Zhang": "UC Berkeley", "Yoshua Bengio": "U. Montreal", "Bo Chen": "National Lab of Radar Signal Processing, School of Electronic Engineering, Xidian University", "Naman Agarwal": "Princeton University", "Hairong Liu": "Baidu Silicon Valley AI Lab", "Nir Baram": "Technion - Israel Institute of Technology", "Francesco Orabona": "Stony Brook University", "Alex Kurakin": "Google Brain", "Kaifeng Lv": "Tsinghua University", "Gergely Neu": "Universitat Pompeu Fabra / Google Brain Z\u00fcrich", "Jianmin Wang": "Tsinghua University", "Bin Hu": "University of Wisconsin", "Yi Zheng": "Duke University", "Andrew Wrigley": "Australian National University", "Alex Gaunt": "Microsoft", "Zhi Jin": "Peking University", "Mingsheng Long": "Tsinghua University", "Andres Masegosa": "University of Almeria", "Sung Ju Hwang": "UNIST / AItrics", "Devdatt Dubhashi": "Chalmers University", "Ananda Suresh": "Google", "Murray Campbell": "IBM", "Evangelos Theodorou": "Georgia Tech", "Mahito Sugiyama": "National Institute of Informatics", "Mark Ho": "Brown University", "Oliver Hinder": "Stanford", "Yew Soon ONG": "Nanyang Technological University", "Orecchia Lorenzo": "Boston", "Christian Sohler": "TU Dortmund", "Chris J Oates": "Newcastle University", "Sanmi Koyejo": "University of Illinois at Urbana-Champaign", "Xinyan Yan": "Georgia Institute of Technology", "Hao Li": "University of Maryland at College Park", "Christoph Lampert": "IST Austria", "Aurelien Lucchi": "ETH", "Dengyong Zhou": "Microsoft Research", "Novi Quadrianto": "University of Sussex and National Research University Higher School of Economics", "Wen Sun": "Carnegie Mellon University", "Ameya Velingker": "", "Hongyu Yang": "Massachusetts Institute of Technology", "Zeyuan Allen-Zhu": "Microsoft Research / Princeton / IAS", "Geoff Gordon": "Carnegie Mellon University", "Shiqian Ma": "The Chinese University of Hong Kong", "Hal Daum\u00e9 III": "University of Maryland", "Vidyashankar Sivakumar": "University of Minnesota", "Georges H\u00e9brail": "EDF Lab Paris-Saclay", "Simon Lacoste-Julien": "University of Montreal", "Nal Kalchbrenner": "DeepMind", "Charles Sutton": "University of Edinburgh", "Ohad Shamir": "Weizmann Institute of Science", "Houfeng Wang": "", "Rupesh Srivastava": "IDSIA (University of Lugano)", "Christos Louizos": "University of Amsterdam", "Branislav Kveton": "Adobe Research", "Michael Mahoney": "UC Berkeley", "Hantian Zhang": "ETH Zurich", "Ann Ragin": "Northwestern University", "Dinh Phung": "Deakin University", "Bill Huang": "Oberlin College", "Mark Rowland": "University of Cambridge", "Scott Reed": "Google Deepmind", "Jonathan How": "MIT", "Yutaka Leon Suematsu": "Google Inc.", "Vu Nguyen": "Deakin University", "Ji Liu": "University of Rochester", "Stephen Tu": "UC Berkeley", "Robert Schapire": "Microsoft Research", "Mathieu Carri\u00e8re": "Inria Saclay", "Xiaoming Yuan": "", "Wenlong Mou": "Peking University", "Jackson Gorham": "STANFORD", "Daniel Tarlow": "Google Brain", "Jieping Ye": "University of Michigan", "Tena Dubcek": "MIT", "Saurabh Goyal": "IBM India Pvt Ltd", "Maxinder S. Kanwal": "UC Berkeley", "Wojciech Czarnecki": "DeepMind", "Vahab Mirrokni": "Google Research", "Tian Gao": "IBM Research", "Russ Salakhutdinov": "Carnegie Mellen University", "Ron Appel": "caltech.edu", "Kimon Fountoulakis": "University of California Berkeley and International Computer Science Institute", "Sathiya Keerthi": "Microsoft", "Haichuan Yang": "University of Rochester", "Yishu Miao": "University of Oxford", "Tom Silver": "Vicarious AI", "Arun Venkatraman": "Carnegie Mellon University", "Renato Leme": "Google Research", "Shie Mannor": "Technion", "Remi Munos": "DeepMind", "Benjamin Van Roy": "Stanford University", "Tuomas Sandholm": "Carnegie Mellon University", "Sungryull Sohn": "University of Michigan", "Weinan E": "Princeton University", "Andrew Selle": "Google Inc.", "An Bian": "ETH Zurich", "Dave Held": "UC Berkeley", "Amin Karbasi": "Yale", "Zina Li": "", "Alon Orlitsky": "UCSD", "Shuai Li": "University of Cambridge", "Hiroshi Kajino": "IBM Research - Tokyo", "Zhenwen Dai": "Amazon.com", "Manik Varma": "Microsoft Research", "Chris Tosh": "University of California, San Diego", "Kevin Winner": "University of Massachusetts, Amherst", "Julian McAuley": "UCSD", "Zachary Lipton": "UCSD", "Brooks Paige": "Alan Turing Institute", "Raquel Urtasun": "University of Toronto", "Christopher Holmes": "University of Oxford", "Edward Grefenstette": "Deepmind", "Iacopo Mastromatteo": "Capital Fund Management", "Zhehui Chen": "Georgia Institute of Technology", "Dmitry Molchanov": "Skoltech", "Xuancheng REN": "Peking University", "Geng Ji": "Brown University", "Lennox Leary": "VUW", "Ari Pakman": "Columbia University", "Venkatesh Saligrama": "Boston University", "Raam Sriram": "DeepMind", "Dina Katabi": "MIT", "Pramod K Varshney": "Syracuse University", "Gautam Kamath": "MIT", "Yann LeCun": "New York University", "Sebastian Pokutta": "Georgia Tech", "Hongyuan Zha": "Georgia Institute of Technology", "Matthew Botvinick": "DeepMind", "Junqi Tang": "the University of Edinburgh", "Charlene Tay": "Indiana University", "Ruben Villegas": "University of Michigan", "Cameron Musco": "", "Ioannis Mitliagkas": "Stanford University", "Xavi Gonzalvo": "", "Qianxiao Li": "Institute of High Performance Computing, A*STAR", "Jonathan Uesato": "MIT", "Hanxiao Liu": "Carnegie Mellon University", "Elisa Celis": "EPFL", "Matthew E. Taylor": "Washington State University", "Nicolas Usunier": "Facebook AI Research", "Carlos Riquelme Ruiz": "Stanford University", "Ines Couso": "University of Oviedo", "HUI Huang": "Shenzhen University", "Cheng Zhang": "Fred Hutchinson Cancer Research Center", "Hong Yu": "University of Massachusetts", "Harsha Vardhan Simhadri": "Microsoft Research", "Hoai Minh Le": "Laboratory of Theoretical and Applied Computer Science, Univ. of Lorraine, Fr", "Tomoya Sakai": "The University of Tokyo / RIKEN", "Moustapha Cisse": "", "lum Maystre": "EPFL", "Nina Balcan": "Carnegie Mellon University", "Ambedkar Dukkipati": "Indian Institute of Science", "Bryan Kian Hsiang Low": "National University of Singapore", "Dan Garber": "TTIC", "Richard E Turner": "University of Cambridge", "Tianbao Yang": "The University of Iowa", "Andrea Hornakova": "Max Planck Institute for Informatics", "Aurelie Lozano": "IBM", "Daniel Kumor": "Purdue University", "Dor Levy": "Tel Aviv University", "Adam Earle": "University of the Witwatersrand", "Murat Kocaoglu": "University of Texas at Austin", "Ming-Min Zhao": "Zhejiang University", "Matthew Schlegel": "Indiana University", "Alexander Pritzel": "Deepmind", "Uri Shalit": "NYU", "J\u00e1nos H\u00f6ner": "TU Berlin / MathPlan", "Steven Wu": "Microsoft Research & U. of Pennsylvania", "Shimon Whiteson": "University of Oxford", "Shinji Watanabe": "MITSUBISHI ELECTRIC RESEARCH LABORATORIES", "Guixiang Ma": "", "Jian Li": "IIIS", "Di Wang": "UC Berkeley", "Eunho Yang": "KAIST / AItrics", "Adam Santoro": "DeepMind", "Simon Osindero": "DeepMind", "Christopher Yau": "University of Birmingham", "Charbel Sakr": "University of Illinois at Urbana-Champaign", "Andy Martin": "Zillow", "Michal Valko": "Inria Lille - Nord Europe", "Eric Wong": "Carnegie Mellon University", "Justin Domke": "University of Massachusetts, Amherst", "Yi Xu": "The University of Iowa", "Souhaib Ben Taieb": "Monash University", "Noam Goldberg": "Bar-Ilan University", "Hamed Hassani": "ETH Zurich", "Andrej Karpathy": "OpenAI", "Joshua Achiam": "UC Berkeley", "Zico Kolter": "Carnegie Mellon University", "Brendan McMahan": "Google", "RAHUL Sukthankar": "Google Research", "Assaf Hallak": "Technion", "Chuyang Ke": "University of Rochester", "Ethan Elenberg": "The University of Texas at Austin", "Gabriel Dulac-Arnold": "Google DeepMind", "David Sussillo": "Google Brain, Google Inc.", "Andreas Damianou": "Amazon.com", "Hieu Pham": "Google", "Jun-ichiro Hirayama": "RIKEN AIP / ATR", "Mike E Davies": "University of Edinburgh", "Kimin Lee": "KAIST", "David Blei": "Columbia University", "Xiao Zhang": "University of Virginia", "Colin Raffel": "Google Brain", "Grzegorz \u015awirszcz": "DeepMind", "Yanzhi Wang": "", "Nhat Ho": "University of Michigan", "Kuniaki Saito": "The University of Tokyo", "Walter Dempsey": "University of Michigan", "Laurent Massouli\u00e9": "MSR-INRIA Joint Center", "Csaba Szepesvari": "University of Alberta", "Ashfaqur Rahman": "CSIRO", "Stanislaw Jastrzebsk": "Jagiellonian University", "Hanjun Dai": "Georgia Tech", "Samuel Schoenholz": "Google Brain", "Tim Harley": "DeepMind", "Sheng Chen": "University of Minnesota", "Oron Anschel": "Technion", "Alekh Agarwal": "Microsoft Research", "Gereon Frahling": "Linguee GmbH", "Barnab\u00e1s P\u00f3czos": "CMU", "Mehrtash Harandi": "Data61", "Tegan Maharaj": "", "Ga\u00ebtan HADJERES": "LIP6 / SONY CSL", "Bo Yang": "University of Minnesota", "Charlotte Laclau": "LIG", "Brandon Amos": "Carnegie Mellon University", "Han Zhu": "Tsinghua University", "Satyen Kale": "Google Research", "Daniel Hernandez-Lobato": "Universidad Autonoma de Madrid", "Vijay Vasudevan": "Google", "Irina Higgins": "DeepMind", "Ahc\u00e8ne Boubekki": "Leuphana University", "Herve Jegou": "Facebook AI Research", "Zhenyao Zhu": "Baidu Silicon Valley AI Lab", "Alexander Rush": "Harvard University", "Pablo Strasser": "HES-UNIGE", "Tsubasa Ochiai": "Doshisha University", "Katherine Heller": "Duke University", "Gael Varoquaux": "Inria", "Arindam Banerjee": "University of Minnesota", "Gregory Diamos": "Baidu Research", "Simon Du": "Carnegie Mellon University", "Guan Wang": "Brown University", "Michael Auli": "Facebook", "Cosmo Zhang": "Purdue University", "Ganzhao Yuan": "SYSU", "Satish Rao": "UC Berkeley", "Alexander Lerchner": "DeepMind", "Pengtao Xie": "Carnegie Mellon University", "Adri\u00e0 Puigdomenech Badia": "Deepmind", "Masashi Sugiyama": "RIKEN / The University of Tokyo", "Tom Goldstein": "University of Maryland", "Yaron Singer": "Harvard", "Chang Xu": "The University of Sydney", "John Lipor": "University of Michigan", "Mahesh Chandra Mukkamala": "Saarland University", "Lihong Li": "Microsoft Research", "Shusen Wang": "UC Berkeley", "Shraman Ray Chaudhuri": "MIT", "Hongteng Xu": "Georgia Institute of Technology", "Cheng Tai": "Peking University", "Krishnakumar Balasubramanian": "Princeton", "Kamalika Chaudhuri": "University of California at San Diego", "Giovanni Zappella": "Amazon Dev Center Germany", "David Carlson": "Duke University", "Marcello Restelli": "Politecnico di Milano", "Adel Elmahdy": "University of Minnesota", "Alp Kucukelbir": "Columbia University", "Misha Denil": "University of Oxford", "Matthew B Blaschko": "KU Leuven", "Jayadev Acharya": "Cornell University", "Linda Smith": "Indiana University", "Monika Henzinger": "", "Thang Luong": "Google Brain", "Hongseok Namkoong": "Stanford University", "Augustus Odena": "Google Brain", "Daniel Zink": "", "Vitaly Kuznetsov": "Google", "Christos Tzamos": "MIT", "John Langford": "Microsoft Research", "Tsung-Hsien Wen": "University of Cambridge", "Sanjiv Kumar": "Google Research, NY", "Liang Zhao": "The City University of New York", "Chris Amato": "Northeastern University", "Deng Cai": "Zhejiang University", "Mukund Sundararajan": "Google Inc.", "Cheng Li": "Deakin University", "Yuexin Wu": "Carnegie Mellon University", "Debadeepta Dey": "Microsoft", "Shashank Singh": "Carnegie Mellon University", "A\u00e4ron van den Oord": "Google", "Chi Jin": "UC Berkeley", "Yann Dauphin": "Facebook AI Research", "Tuo Zhao": "Georgia Institute of Technology", "Junxiang Chen": "Northeastern University", "Shai Shalev-Shwartz": "", "Zhao Song": "UT-Austin", "Oskar Schneider": "", "Tongliang Liu": "The University of Sydney", "Quynh Nguyen": "Saarland University", "Arun SUGGALA": "Carnegie Mellon University", "Yu-Xiang Wang": "Carnegie Mellon University / Amazon AWS", "Alon Brutzkus": "Tel Aviv University", "Amr Ahmed": "Google", "Yoshitaka Ushiku": "The University of Tokyo", "Benjamin Moseley": "Washington University in St. Louis", "Poan Wang": "Academia sinica", "Eiichi Matsumoto": "Preferred Networks Inc.", "Masaaki Imaizumi": "Institute of Statistical Mathematics", "Piotr Bojanowski": "Facebook"}]