Stars
Graph Neural Network Library for PyTorch
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Linear solvers in JAX and Equinox. https://docs.kidger.site/lineax
Optax is a gradient processing and optimization library for JAX.
Hardware accelerated, batchable and differentiable optimizers in JAX.
PyTorch implementation of Ryan Keisler's 2022 "Forecasting Global Weather with Graph Neural Networks" paper (https://arxiv.org/abs/2202.07575)