Fast and flexible AutoML with learning guarantees.

Highly cited and useful papers related to machine learning, deep learning, AI, game theory, reinforcement learning

🔬 Research Framework for Single and Multi-Players 🎰 Multi-Arms Bandits (MAB) Algorithms, implementing all the state-of-the-art algorithms for single-player (UCB, KL-UCB, Thompson...) and multi-player (MusicalChair, MEGA, rhoRand, MCTop/RandTopM etc).. Available on PyPI: https://pypi.org/project/SMPyBandits/ and documentation on

Repository for collection of research papers on privacy.

Distributional Generalization in NLP. A roadmap.

AI Learning Hub for Machine Learning, Deep Learning, Computer Vision and Statistics

The first comprehensive Lean 4 formalization of statistical learning theory, featuring Gaussian Lipschitz concentration and Dudley's entropy integral-establishes a reusable foundation for formalizing ML theory.

Model Zoos for Continual Learning (ICLR 22)

Formal Psychological Models of Categorization and Learning

Scinis-learn is a package of non-OOP functions for Machine Learning developed by young Moroccan AI engineering students from scratch.

Material for 'Mathematics of Deep Learning Workshop' (Invited Talk)

#UAI2020 Codes for PAC-Bayesian Contrastive Unsupervised Representation Learning

Code for paper "Efficient Sparse Coding using Hierarchical Riemannian Pursuit," in IEEE Transactions on Signal Processing, Y. Xue, V. K. N. Lau and S. Cai, doi: 10.1109/TSP.2021.3093769.

Official implementation of On-Demand Sampling: Learning Optimally from Multiple Distributions (Neurips 2022)

Solutions and Codes Example for Assignments of Machine Learning Foundation, Fall 2020, National Taiwan University

A Python implementation of the Neural Tangent Kernel (jacot et al, 2018)

Official code for Paper: "Can One Modality Model Synergize Training of Other Modality Models?" implemented in PyTorch

Implementation of https://arxiv.org/abs/2106.03027

source code of NeurIPS 2021 paper: "Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound"

A program that learns your polynomial using just two queries

PAC-Bayesian Binary Activated Deep Neural Networks

This repository contains the code to reproduce all of the results in our paper: Making Learners (More) Monotone, T J Viering, A Mey, M Loog, IDA 2020.

Codebase for "A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models", published at ICML 2024.

Course Design Lab Repository

Investigating the mathematical properties of data generated from diffusion models

Learning ReLU networks to high uniform accuracy is intractable (ICLR 2023)

Python code for the post "Binary Search on Graphs"

Linear-time sequence modeling that replaces attention's O(n²d) complexity with O(nd) summation-based aggregation. Demonstrates constraint-driven emergence: how functional representations can develop from optimization pressure and architectural constraints alone, without explicit pairwise interactions.

Official code for k-experts - Online Policies and Fundamental Limits, AISTATS 2022

Code for the paper "Interpolation can hurt robust generalization even when there is no noise" available here: https://papers.nips.cc/paper/2021/hash/c4f2c88e16a579900657c18726641c81-Abstract.html