jaxopt

Deep learning optimizer

An open-source project providing hardware accelerated, batchable and differentiable optimizers in JAX for deep learning.

Hardware accelerated, batchable and differentiable optimizers in JAX.

GitHub

941 stars
18 watching
67 forks
Language: Python
last commit: about 2 years ago
Linked from 1 awesome list

bi-leveldeep-learningdifferentiable-programmingjaxoptimization

Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
google-deepmind/optaxA gradient processing and optimization library designed to facilitate research and productivity in machine learning by providing building blocks for custom optimizers and gradient processing components.1,730
google-deepmind/kfac-jaxLibrary providing an implementation of the K-FAC optimizer and curvature estimator for second-order optimization in neural networks.252
locuslab/optnetA PyTorch module that adds differentiable optimization as a layer to neural networks517
davisyoshida/loraxA JAX transform that simplifies the training of large language models by reducing memory usage through low-rank adaptation.134
aqibsaeed/genetic-cnnA tool for exploring and optimizing the architecture of Convolutional Neural Networks using a Genetic Algorithm218
darshandeshpande/jax-modelsProvides a collection of deep learning models and utilities in JAX/Flax for research purposes.151
jankrepl/deepdowA framework that enables portfolio optimization using deep learning.932
jycouet/kitqlA collection of standalone tools to speedrun web applications built with GraphQL and Svelte409
google-deepmind/jraphA lightweight library for working with graph neural networks in jax.1,380
google-deepmind/jaxlineProvides a Python-based framework for building distributed JAX training and evaluation experiments153
deng-cy/deep_learning_topology_optOptimization code for topology optimization problems using machine learning and deep learning techniques107
deependersingla/deep_portfolioAn algorithm that optimizes portfolio allocation using Reinforcement Learning and Supervised learning.168
google-deepmind/chexA set of utilities for writing reliable JAX code797
hyperopt/hyperopt-sklearnAutomates search for optimal parameters in machine learning algorithms.1,594
xternalz/sdpointA deep learning method for optimizing convolutional neural networks by reducing computational cost while improving regularization and inference efficiency.18