On the well-posedness of Bayesian inverse problems

Abstract

The subject of this article is the introduction of a new concept of well-posedness of Bayesian inverse problems. The conventional concept of (Lipschitz, Hellinger) well-posedness in [Stuart 2010, Acta Numerica 19, pp. 451-559] is difficult to verify in practice and may be inappropriate in some contexts. Our concept simply replaces the Lipschitz continuity of the posterior measure in the Hellinger distance by continuity in an appropriate distance between probability measures. Aside from the Hellinger distance, we investigate well-posedness with respect to weak convergence, the total variation distance, the Wasserstein distance, and also the Kullback--Leibler divergence. We demonstrate that the weakening to continuity is tolerable and that the generalisation to other distances is important. The main results of this article are proofs of well-posedness with respect to some of the aforementioned distances for large classes of Bayesian inverse problems. Here, little or no information about the underlying model is necessary; making these results particularly interesting for practitioners using black-box models. We illustrate our findings with numerical examples motivated from machine learning and image processing.

arXiv comment30 pages, 7 figures

References in corpus (7)

• Sparse Deterministic Approximation of Bayesian Inverse Problems
• Bayesian Probabilistic Numerical Methods
• Well-Posed Bayesian Geometric Inverse Problems Arising in Subsurface Flow
• Bayesian Posterior Contraction Rates for Linear Severely Ill-posed Inverse Problems
• Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
• Fast sampling of parameterised Gaussian random fields
• Bayesian parameter identification in Cahn-Hilliard models for biological growth

Cited by in corpus (11)

• Γ-convergence of Onsager-Machlup functionals. Part I: With applications to maximum a posteriori estimation in Bayesian inverse problems
• Generalized Parallel Tempering on Bayesian Inverse Problems
• Multilevel adaptive sparse Leja approximations for Bayesian inverse problems
• Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie
• On Bayesian data assimilation for PDEs with ill-posed forward problems
• Error bounds for some approximate posterior measures in Bayesian inference
• On Unifying Randomized Methods For Inverse Problems
• Stability of Gibbs Posteriors from the Wasserstein Loss for Bayesian Full Waveform Inversion
• Bayesian Imaging With Data-Driven Priors Encoded by Neural Networks: Theory, Methods, and Algorithms
• Nonparametric Bayesian inference of discretely observed diffusions
• Well-posedness of Bayesian inverse problems for hyperbolic conservation laws