Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.
APACHE-2.0 License
Bot releases are hidden (Show)
Published by patrick-kidger over 3 years ago
Initial release to PyPI.
Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotl...
Software Architecture for ML engineers
Differentiable computations of the signature and logsignature transforms, on both CPU and GPU. (I...
C++ library based on tensorrt integration
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (par...
PyTorch tutorials and best practices.
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.
Interpolating natural cubic splines. Includes batching, GPU support, support for missing values, ...
Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)