evosax
Evolution Optimizer Library
An evolution strategy optimization library built on top of JAX and XLA for high-throughput acceleration
Evolution Strategies in JAX 🦎
514 stars
10 watching
43 forks
Language: Python
last commit: almost 2 years agoLinked from 1 awesome list
Related projects:
| Repository | Description | Stars |
|---|---|---|
| An evolutionary computation library built on top of PyTorch for solving optimization problems in various fields. | 1,026 | |
| An optimization technique based on ideas of adaptation and evolution for training neural networks | 270 | |
| A Python library for multiobjective optimization algorithms and analysis tools. | 579 | |
| An optimization library based on nature-inspired meta-heuristic algorithms. | 609 | |
| 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. | 1,730 | |
| A JAX transform that simplifies the training of large language models by reducing memory usage through low-rank adaptation. | 134 | |
| An open-source project providing hardware accelerated, batchable and differentiable optimizers in JAX for deep learning. | 941 | |
| An evolutionary optimization library that provides multiple algorithms and interfaces to solve complex optimization problems using genetic and other optimization techniques. | 890 | |
| A framework that accelerates RL environment processes by leveraging JAX and GPU acceleration | 669 | |
| An implementation of the Neuroevolution through Augmenting Topologies (NEAT) algorithm for evolutionary optimization of neural networks in Pharo. | 16 | |
| A Python framework for using genetic programming to solve problems and optimize solutions | 122 | |
| An algorithmic optimization tool inspired by genetic algorithms and Soylent's DIY nutritional mix, aiming to create optimal recipes for personalized nutrition. | 18 | |
| Tools for assessing optimal designs for hybrid energy plants | 25 | |
| A collection of standalone tools to speedrun web applications built with GraphQL and Svelte | 409 | |
| An implementation of a genetic algorithm and particle swarm optimization in Go to find the maximum value of a 3D function. | 33 |