kfac-jax
KFAC optimizer
Library providing an implementation of the K-FAC optimizer and curvature estimator for second-order optimization in neural networks.
Second Order Optimization and Curvature Estimation with K-FAC in JAX.
248 stars
11 watching
24 forks
Language: Python
last commit: 5 days ago
Linked from 1 awesome list
bayesian-deep-learningmachine-learningoptimization
n2cholas/awesome-jaxRelated projects:
| Repository | Description | Stars |
|---|---|---|
 google/jaxopt | An open-source project providing hardware accelerated, batchable and differentiable optimizers in JAX for deep learning. | 933 |
| google-deepmind/optax | A 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. | 1,697 |
| google-deepmind/jraph | A lightweight library for working with graph neural networks in jax. | 1,375 |
 kvcache-ai/ktransformers | A flexible framework for LLM inference optimizations with support for multiple models and architectures | 736 |
 darshandeshpande/jax-models | Provides a collection of deep learning models and utilities in JAX/Flax for research purposes. | 151 |
 guillaume-chevalier/hyperopt-keras-cnn-cifar-100 | Automates hyperparameter optimization and neural network architecture search using Hyperopt on a CNN model for the CIFAR-100 dataset | 106 |
 alonfnt/bayex | An implementation of Bayesian optimization using Gaussian process regression and JAX for efficient numerical computations | 84 |
 matthias-wright/flaxmodels | Provides pre-trained deep learning models for the Jax/Flax ecosystem. | 238 |
 aqibsaeed/genetic-cnn | A tool for exploring and optimizing the architecture of Convolutional Neural Networks using a Genetic Algorithm | 218 |
 lucfra/far-ho | A package for optimizing hyperparameters and meta-learning using gradient-based methods in TensorFlow. | 187 |
| google-deepmind/tf2jax | Converts TensorFlow functions to equivalent JAX Python functions. | 105 |
 deng-cy/deep_learning_topology_opt | A toolkit for using machine learning to optimize complex geometries in simulations | 107 |
 neuralmagic/sparseml | Enables the creation of smaller neural network models through efficient pruning and quantization techniques | 2,071 |
 guopengf/auto-fedrl | A reinforcement learning-based framework for optimizing hyperparameters in distributed machine learning environments. | 15 |
 intel/neural-compressor | Tools and techniques for optimizing large language models on various frameworks and hardware platforms. | 2,226 |