google-research/torchsde

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

72
/ 100
Verified

Implements multiple SDE solver algorithms (Euler, Milstein, adaptive-step) with configurable noise types (scalar, diagonal, general) and supports both Itô and Stratonovich calculus. Enables end-to-end learning of latent SDEs and neural SDE-based generative models through PyTorch autograd, with adjoint-based sensitivity analysis for memory-efficient backpropagation. Integrates seamlessly with PyTorch's `nn.Module` API and demonstrated on applications including VAE-style latent dynamics and adversarial SDE training.

1,708 stars and 1,988,417 monthly downloads. Used by 8 other packages. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 25 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

1,708

Forks

223

Language

Python

License

Apache-2.0

Last pushed

Dec 30, 2024

Monthly downloads

1,988,417

Commits (30d)

0

Dependencies

4

Reverse dependents

8

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google-research/torchsde"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.