Alternatives and similar repositories for top-sgd

Users that are interested in top-sgd are comparing it to the libraries listed below

• lixilinx / psgd_torch
  Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…
  ☆188Updated this week
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆92Updated last year
• stanislavfort / dissect-git-re-basin
  Replicating and dissecting the git-re-basin project in one-click-replication Colabs
  ☆37Updated 3 years ago
• facebookresearch / w2ot
  Euclidean Wasserstein-2 optimal transportation
  ☆47Updated 2 years ago
• bremen79 / parameterfree
  Parameter-Free Optimizers for Pytorch
  ☆130Updated last year
• shikaiqiu / compute-better-spent
  ☆62Updated last year
• shyamsn97 / hyper-nn
  Easy Hypernetworks in Pytorch and Jax
  ☆106Updated 2 years ago
• cgarciae / nanoGPT-jax
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆37Updated 2 years ago
• davisyoshida / lorax
  LoRA for arbitrary JAX models and functions
  ☆143Updated last year
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆63Updated 4 years ago
• mgrankin / minGPT
  minGPT in JAX
  ☆48Updated 3 years ago
• google-deepmind / eigengame
  Open source code for EigenGame.
  ☆34Updated 2 years ago
• formll / dog
  DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
  ☆63Updated 2 years ago
• thjashin / multires-conv
  Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)
  ☆127Updated 2 years ago
• AhmedImtiazPrio / grok-adversarial
  Deep Networks Grok All the Time and Here is Why
  ☆38Updated last year
• google-deepmind / conformal_training
  This repository contains a Jax implementation of conformal training corresponding to the ICLR'22 paper "learning optimal conformal classi…
  ☆130Updated 3 years ago
• tristandeleu / jax-meta-learning
  A collection of meta-learning algorithms in Jax
  ☆23Updated 3 years ago
• google-deepmind / dks
  Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural netwo…
  ☆74Updated 5 months ago
• young-geng / scalax
  A simple library for scaling up JAX programs
  ☆144Updated last month
• phlippe / jax_trainer
  Lightning-like training API for JAX with Flax
  ☆44Updated last year
• google-research / jaxpruner
  ☆233Updated 10 months ago
• AllanYangZhou / universal_neural_functional
  ☆54Updated last year
• aks2203 / easy-to-hard
  Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"
  ☆60Updated 3 years ago
• locuslab / edge-of-stability
  ☆73Updated last year
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆69Updated last year
• gpauloski / kfac-pytorch
  Distributed K-FAC preconditioner for PyTorch
  ☆93Updated last week
• nikhilvyas / SOAP
  ☆230Updated last year
• johnryan465 / pscan
  ☆40Updated last year
• Ping-C / optimizer
  This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…
  ☆40Updated 2 years ago
• JesseFarebro / flax-mup
  Maximal Update Parametrization (μP) with Flax & Optax.
  ☆16Updated 2 years ago