Patrick Kidger
Patrick Kidger
mkposters
Make posters from Markdown files.
signatory
Differentiable computations of the signature and logsignature transforms, on both CPU and GPU. (ICLR 2021)
equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
torchtyping
Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.
NeuralCDE
Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)
torchcde
Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.
jaxtyping
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
torchcubicspline
Interpolating natural cubic splines. Includes batching, GPU support, support for missing values, evaluating derivatives of the spline, and backpropagation.