A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...

Code for Arxiv Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle

MDL Complexity computations and experiments from the paper "Revisiting complexity and the bias-variance tradeoff".

Double Descent results for FCNNs on MNIST, extended by Label Noise (Reconciling Modern Machine-Learning Practice and the Classical Bias–Variance Trade-Off) [Python/PyTorch]..

Explore the double-descent phenomena in the context of system identification. Companion code to the paper (https://arxiv.org/abs/2012.06341):

[ICIAP23] Sparse Double Descent in Vision Transformers: real or phantom threat?

This repository is the official implementation of "Optimization Variance: Delve into the Epoch-Wise Double Descent of DNNs"

[AAAI24] DSD2: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?

Double descent experiments/repros on classical ML models and deep neural nets

This project outlines 4 experiments to explore the effects of several settings on the bias-variance tradeoff curve

Assignments of my CST Part II Deep Neural Networks unit

A Review of Preetum Nakkiran's "More Data Can Hurt for Linear Regression: Sample-wise Double Descent"

Implementation of the double descent Deep Learning phenomenon from the article Grokking: Generalization beyond overfitting.

ICLR 2022: Phenomenology of Double Descent in Finite-width Neural Networks

Interpreting double descent phenomenon in neural networks by varying model depth and tracking train loss, test loss, and effective dimensionality.

Toy dataset to study double descent optimization patterns in machine learning.

DSC 261 Responsible Data Science Project

Interpolating Neural Networks in Asset Pricing Data. Supports Distributed Training in TensorFlow.

This assignment repository demonstrates the existance of deep double descent phenomena for the deep learning models usually encorporated with a clinical context. For this, a famous ECG dataset, PTBXL has been employed.

A comprehensive data science and ML project portfolio - featuring six end-to-end projects. Showcases expertise in unsupervised clustering, supervised classification and regression, deep learning architectures, advanced feature selection, and full-stack web application deployment across healthcare, finance, bioinformatics, and real estate domains.