Become a sponsor to Patrick Kidger
I work in scientific machine learning: combining deep learning with differential equations.
A few projects I'm proud of:
- Differential equation solvers in JAX: Diffrax;
- Differential equation solvers in PyTorch: torchsde, torchcde;
- Tensor type annotations (inc. shape, dtypes, ...) for JAX/NumPy/PyTorch: jaxtyping;
- Neural networks in JAX, elegantly: Equinox.
See also:
Please feel free to use my work without sponsorship! A few kind souls asked for this as a way to say thanks :)
Featured work
-
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.
Python 1,580 -
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Python 1,431 -
patrick-kidger/torchcde
Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.
Python 420 -
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
Python 2,104 -
patrick-kidger/torchtyping
Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.
Python 1,403