Probabilistic ODE Solvers with Runge-Kutta Means

Abstract

Runge-Kutta methods are the classic family of solvers for ordinary differential equations (ODEs), and the basis for the state of the art. Like most numerical methods, they return point estimates. We construct a family of probabilistic numerical methods that instead return a Gauss-Markov process defining a probability distribution over the ODE solution. In contrast to prior work, we construct this family such that posterior means match the outputs of the Runge-Kutta family exactly, thus inheriting their proven good properties. Remaining degrees of freedom not identified by the match to Runge-Kutta are chosen such that the posterior probability measure fits the observed structure of the ODE. Our results shed light on the structure of Runge-Kutta solvers from a new direction, provide a richer, probabilistic output, have low computational cost, and raise new research questions.

18 pages (9 page conference paper, plus supplements); appears in Advances in Neural Information Processing Systems (NIPS), 2014

Cited by in corpus (20)

• Neural Ordinary Differential Equations
• Physics-Informed CoKriging: A Gaussian-Process-Regression-Based Multifidelity Method for Data-Model Convergence
• Gamblets for opening the complexity-bottleneck of implicit schemes for hyperbolic and parabolic ODEs/PDEs with rough coefficients
• Frank-Wolfe Bayesian Quadrature: Probabilistic Integration with Theoretical Guarantees
• Active Uncertainty Calibration in Bayesian ODE Solvers
• Solving and Learning Nonlinear PDEs with Gaussian Processes
• A probabilistic finite element method based on random meshes: Error estimators and Bayesian inverse problems
• Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems
• Stable Implementation of Probabilistic ODE Solvers
• Probabilistic ODE Solutions in Millions of Dimensions
• Consistency and convergence of simulation schemes in Information field dynamics
• Transfer Learning using Neural Ordinary Differential Equations
• Nonnegativity-Enforced Gaussian Process Regression
• A Role for Symmetry in the Bayesian Solution of Differential Equations
• Model-based Kernel Sum Rule: Kernel Bayesian Inference with Probabilistic Models
• Sampling Methods for Bayesian Inference Involving Convergent Noisy Approximations of Forward Maps
• Aligned Multi-Task Gaussian Process
• Black Box Probabilistic Numerics
• Dynamical field inference and supersymmetry
• Comments on the article "A Bayesian conjugate gradient method"