Alternatives and similar repositories for learned_optimization

Users that are interested in learned_optimization are comparing it to the libraries listed below

• kach / gradient-descent-the-ultimate-optimizer
  Code for our NeurIPS 2022 paper
  ☆372Updated 2 years ago
• google / ml_collections
  ML Collections is a library of Python Collections designed for ML use cases.
  ☆1,004Updated last month
• pytorch / tensordict
  TensorDict is a pytorch dedicated tensor container.
  ☆995Updated last week
• nnaisense / evotorch
  Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.
  ☆1,111Updated 3 weeks ago
• pytorch / functorch
  functorch is JAX-like composable function transforms for PyTorch.
  ☆1,437Updated 4 months ago
• archinetai / surgeon-pytorch
  A library to inspect and extract intermediate layers of PyTorch models.
  ☆475Updated 3 years ago
• xl0 / lovely-tensors
  Tensors, for human consumption
  ☆1,337Updated last month
• microsoft / mup
  maximal update parametrization (µP)
  ☆1,644Updated last year
• f-dangel / cockpit
  Cockpit: A Practical Debugging Tool for Training Deep Neural Networks
  ☆485Updated 3 years ago
• mlcommons / algorithmic-efficiency
  MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvement…
  ☆404Updated 2 weeks ago
• facebookresearch / torchdim
  Named tensors with first-class dimensions for PyTorch
  ☆332Updated 2 years ago
• facebookresearch / optimizers
  For optimization algorithm research and development.
  ☆555Updated last week
• facebookresearch / dadaptation
  D-Adaptation for SGD, Adam and AdaGrad
  ☆528Updated 11 months ago
• BlackHC / toma
  Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory
  ☆438Updated last year
• mpezeshki / pytorch_forward_forward
  Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation
  ☆1,490Updated 2 years ago
• metaopt / torchopt
  TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
  ☆622Updated last month
• lucidrains / lion-pytorch
  🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
  ☆2,180Updated last year
• srush / annotated-s4
  Implementation of https://srush.github.io/annotated-s4
  ☆510Updated 6 months ago
• samuela / git-re-basin
  Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"
  ☆500Updated 2 years ago
• google / fiddle
  ☆371Updated last month
• Liuhong99 / Sophia
  The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
  ☆981Updated last year
• tysam-code / hlb-CIFAR10
  Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
  ☆1,299Updated last year
• patrick-kidger / torchtyping
  Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.
  ☆1,466Updated 8 months ago
• facebookresearch / bitsandbytes
  Library for 8-bit optimizers and quantization routines.
  ☆781Updated 3 years ago
• hristo-vrigazov / mmap.ninja
  Memory mapped numpy arrays of varying shapes
  ☆307Updated last year
• NVIDIA-Merlin / dataloader
  The merlin dataloader lets you rapidly load tabular data for training deep leaning models with TensorFlow, PyTorch or JAX
  ☆422Updated last year
• google / CommonLoopUtils
  CLU lets you write beautiful training loops in JAX.
  ☆362Updated last week
• meta-pytorch / torcheval
  A library that contains a rich collection of performant PyTorch model metrics, a simple interface to create new metrics, a toolkit to fac…
  ☆245Updated last week
• vopani / jaxton
  100 exercises to learn JAX
  ☆595Updated 3 years ago
• google-deepmind / chex
  ☆909Updated last week