Probabilistic Numerics in Python.

Probabilistic Numerical Differential Equation solvers via Bayesian filtering and smoothing

Probabilistic solvers for differential equations in JAX. Adaptive ODE solvers with calibration, state-space model factorisations, and custom information operators. Compatible with the broader JAX scientific computing ecosystem.

IterGP: Computation-Aware Gaussian Process Inference (NeurIPS 2022)

Code for the Paper "Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers"

Probabilistic ODE solvers are fun, but are they fast? See also: https://github.com/pnkraemer/probdiffeq for JAX code or https://github.com/nathanaelbosch/ProbNumDiffEq.jl for Julia code.

Physics-Enhanced Regression for Initial Value Problems

Computation-Aware Kalman Filtering and RTS Smoothing

Python tools for solving data-constrained finite element problems

Probabilistic numerical finite differences. Compute finite difference weights and differentiation matrices on scattered data sites and with out-of-the-box uncertainty quantification.

Efficient SDE samplers including Gaussian-based probabilistic solvers. Written in JAX.

Code for the paper "Computation-Aware Kalman Filtering and Smoothing"

Information and materials for Google Summer of Code participants developing for ProbNum.

Evaluate the accuracy, efficiency, and uncertainty-calibration of probabilistic numerical algorithms.

Probabilistic Linear Solvers for Machine Learning (NeurIPS 2020)

Website of the Probabilistic Numerics community.

Probabilistic numerical integration framework: Bayesian Quadrature with Gaussian Process priors, classical quadrature rules, Monte Carlo methods, active sampling, and uncertainty quantification.

Code for the manuscript "A probabilistic diagnostic for Laplace approximations: Introduction and experimentation"

Published asv benchmark reports and database of ProbNum.

Numerical Integration Methods and Probabilistic Methods for generating random numbers.