patrick-kidger/diffrax
patrick-kidger/diffrax has 2,130 GitHub stars and 205 forks. GitHot measured +1 stars in 24 hours, +4 in 7 days, and +8 in 15 days. Last checked 2026-11-22 11:18 UTC. Last push 2026-09-06.
計測したスター増加
- 24時間
- +1
- 7日間
- +4
- 15日間
- +8
- 1か月
- 履歴を収集中
期間ごとの純増数です。期間は重複しており、日別の値ではありません。未計測の値は空欄です。スター数は注目度の指標であり、品質の保証ではありません。
概要
JAX用の数値微分方程式ソルバー。自動微分とGPUに対応しています。https://docs.kidger.site/diffrax/
機械学習README.md
オリジナルDiffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable.
Diffrax is a JAX-based library providing numerical differential equation solvers.
Features include:
- ODE/SDE/CDE (ordinary/stochastic/controlled) solvers;
- lots of different solvers (including
Tsit5,Dopri8, symplectic solvers, implicit solvers); - vmappable everything (including the region of integration);
- using a PyTree as the state;
- dense solutions;
- multiple adjoint methods for backpropagation;
- support for neural differential equations.
From a technical point of view, the internal structure of the library is pretty cool -- all kinds of equations (ODEs, SDEs, CDEs) are solved in a unified way (rather than being treated separately), producing a small tightly-written library.
Installation
pip install diffrax
Requires Python 3.10+.
Documentation
Available at https://docs.kidger.site/diffrax.
Quick example
from diffrax import diffeqsolve, ODETerm, Dopri5
import jax.numpy as jnp
def f(t, y, args):
return -y
term = ODETerm(f)
solver = Dopri5()
y0 = jnp.array([2., 3.])
solution = diffeqsolve(term, solver, t0=0, t1=1, dt0=0.1, y0=y0)
Here, Dopri5 refers to the Dormand--Prince 5(4) numerical differential equation solver, which is a standard choice for many problems.
Citation
If you found this library useful in academic research, please cite: (arXiv link)
@phdthesis{kidger2021on,
title={{O}n {N}eural {D}ifferential {E}quations},
author={Patrick Kidger},
year={2021},
school={University of Oxford},
}
(Also consider starring the project on GitHub.)
See also: other libraries in the JAX ecosystem
Always useful
Equinox: neural networks and everything not already in core JAX!
jaxtyping: type annotations for shape/dtype of arrays.
Deep learning
Optax: first-order gradient (SGD, Adam, ...) optimisers.
Orbax: checkpointing (async/multi-host/multi-device).
Levanter: scalable+reliable training of foundation models (e.g. LLMs).
paramax: parameterizations and constraints for PyTrees.
Scientific computing
Optimistix: root finding, minimisation, fixed points, and least squares.
Lineax: linear solvers.
BlackJAX: probabilistic+Bayesian sampling.
sympy2jax: SymPy<->JAX conversion; train symbolic expressions via gradient descent.
PySR: symbolic regression. (Non-JAX honourable mention!)
Awesome JAX
Awesome JAX: a longer list of other JAX projects.
関連プロジェクトを探す
読み込み中…