On the Local Lipschitz Stability of Bayesian Inverse Problems

Abstract

In this note we consider the stability of posterior measures occuring in Bayesian inference w.r.t. perturbations of the prior measure and the log-likelihood function. This extends the well-posedness analysis of Bayesian inverse problems. In particular, we prove a general local Lipschitz continuous dependence of the posterior on the prior and the log-likelihood w.r.t. various common distances of probability measures. These include the total variation, Hellinger, and Wasserstein distance and the Kullback-Leibler divergence. We only assume the boundedness of the likelihoods and measure their perturbations in an $L^p$-norm w.r.t. the prior. The obtained stability yields under mild assumptions the well-posedness of Bayesian inverse problems, in particular, a well-posedness w.r.t. the Wasserstein distance. Moreover, our results indicate an increasing sensitivity of Bayesian inference as the posterior becomes more concentrated, e.g., due to more or more accurate data. This confirms and extends previous observations made in the sensitivity analysis of Bayesian inference.

arXiv comment28 pages

References in corpus (6)

• On the Bernstein-von Mises phenomenon for nonparametric Bayes procedures
• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• On the Brittleness of Bayesian Inference
• Brittleness of Bayesian Inference Under Finite Information in a Continuous World
• Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
• Perturbation Bounds for Monte Carlo within Metropolis via Restricted Approximations

Cited by in corpus (5)

• Γ-convergence of Onsager-Machlup functionals. Part I: With applications to maximum a posteriori estimation in Bayesian inverse problems
• Stability estimates for the expected utility in Bayesian optimal experimental design
• On Bayesian data assimilation for PDEs with ill-posed forward problems
• Choosing observation operators to mitigate model error in Bayesian inverse problems
• Error bounds for some approximate posterior measures in Bayesian inference