ott
Optimal matcher
A JAX-based library for computing optimal transport problems in various settings
Optimal transport tools implemented with the JAX framework, to get differentiable, parallel and jit-able computations.
550 stars
10 watching
82 forks
Language: Python
last commit: about 2 months ago
Linked from 1 awesome list
automatic-differentiationgromov-wassersteinjaxoptimal-transportsinkhorn
n2cholas/awesome-jaxRelated projects:
| Repository | Description | Stars |
|---|---|---|
 eniac/otti | A compiler and solver for optimization problems using zkSNARKs | 6 |
 google/jaxopt | An open-source project providing hardware accelerated, batchable and differentiable optimizers in JAX for deep learning. | 941 |
 dipolar-quantum-gases/jaxfit | A package for GPU/TPU accelerated nonlinear least-squares curve fitting using JAX | 53 |
 stevengj/nlopt | Provides a unified interface to multiple nonlinear optimization algorithms for global and local problem-solving in various fields | 1,908 |
 jmrichardson/tuneta | Automates optimization of technical indicators for machine learning models in finance | 421 |
 locuslab/optnet | A PyTorch module that adds differentiable optimization as a layer to neural networks | 517 |
 sidak/otfusion | Model fusion via optimal transport to combine performance of multiple machine learning models | 136 |
 hyperopt/hyperopt-sklearn | Automates search for optimal parameters in machine learning algorithms. | 1,594 |
 osqp/osqpth | A PyTorch module that wraps the OSQP solver for differentiable optimization problems | 59 |
 stunkymonkey/osm_ch | A tool that uses graph contraction hierarchies to speed up shortest path calculations on OpenStreetMap data | 17 |
 matthewpeterkelly/optimtraj | A software package that optimizes trajectories for physical systems by finding the optimal sequence of controls to minimize energy or cost | 636 |
 jiangoforit/yellowfin_pytorch | An optimizer that automatically tunes momentum and learning rate using local quadratic approximation. | 287 |
 jycouet/kitql | A collection of standalone tools to speedrun web applications built with GraphQL and Svelte | 409 |
 metaopt/torchopt | An efficient library for differentiable optimization built on top of PyTorch. | 554 |
 stonesjtu/pytorch-nce | An implementation of Noise Contrastive Estimation in PyTorch to improve the performance and efficiency of softmax output layers | 317 |