(ICML 2026) TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning

ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE

[ICML 2026] Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling

Курс "Введение в глубокое обучение" для бакалавров 3 курса кафедры ММП ВМК МГУ, весенний семестр

(ICML 2026) GraphPFN: A Prior-Data Fitted Graph Foundation Model

Muon is an optimizer for hidden layers in neural networks

Library for FO Optimization

[ICLR 2026] GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver

lightweight optimizer benchmark

"Aligning Distributionally Robust Optimization with Practical Deep Learning Needs"

Spatiotemporal forecasting with PyTorch and DGL.

PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..

Efficient optimizers

A LinearOperator implementation to wrap the numerical nuts and bolts of GPyTorch

Efficient Deep Learning Systems course materials

This repository contains the code for the paper titled "Mosaic-skeleton approximation is all you need for Smoluchowski equations"

(ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling

Benchmark for quadratic programming solvers available in Python

Low-rank Monte-Carlo simulation for aggregation-fragmentation kinetics