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