Gaussian processes for Bayesian inverse problems associated with linear partial differential equations

Abstract

This work is concerned with the use of Gaussian surrogate models for Bayesian inverse problems associated with linear partial differential equations. A particular focus is on the regime where only a small amount of training data is available. In this regime the type of Gaussian prior used is of critical importance with respect to how well the surrogate model will perform in terms of Bayesian inversion. We extend the framework of Raissi et. al. (2017) to construct PDE-informed Gaussian priors that we then use to construct different approximate posteriors. A number of different numerical experiments illustrate the superiority of the PDE-informed Gaussian priors over more traditional priors.

References in corpus (8)

• MCMC using Hamiltonian dynamics
• Machine Learning of Linear Differential Equations using Gaussian Processes
• Firedrake: automating the finite element method by composing abstractions
• Active subspace methods in theory and practice: applications to kriging surfaces
• Probabilistic Numerical Methods for PDE-constrained Bayesian Inverse Problems
• Iterative Updating of Model Error for Bayesian Inversion
• Random forward models and log-likelihoods in Bayesian inverse problems
• Images of Gaussian and other stochastic processes under closed, densely-defined, unbounded linear operators

Cited by in corpus (1)

• Bayesian Parameter Inference and Uncertainty Quantification for a Computational Pulmonary Hemodynamics Model Using Gaussian Processes