Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Hardware accelerated, batchable and differentiable optimizers in JAX.

Gaussian processes in JAX and Flax.

MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.

Rax is a Learning-to-Rank library written in JAX.

Mathematical operations for JAX pytrees

Concise deep learning for JAX

Robust Bi-Tempered Logistic Loss Based on Bregman Divergences. https://arxiv.org/pdf/1906.03361.pdf

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Flax is a neural network library for JAX that is designed for flexibility.