On the local Lipschitz stability of Bayesian inverse problems

DOI10.1088/1361-6420/AB6F43MaRDI QIDQ5000612zbMATH OpenOpenAlexFDO

Authors Björn Sprungk

Publication date 14 July 2021

Published in Inverse Problems (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1906.07120

zbMATH Keywords

Bayesian inferencerobust statisticsWasserstein distanceKullback-Leibler divergenceinverse problemswell-posednessHellinger distance

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Bayesian inference (62F15)

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.

Recommendations

• On the well-posedness of Bayesian inverse problems
• Well-Posed Bayesian Inverse Problems: Priors with Exponential Tails
• Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
• Stability and infinitesimal robustness of posterior distributions and posterior quantities
• Posterior consistency for Bayesian inverse problems through stability and regression results

Cites work

• scientific article; zbMATH DE number 9256 (Why is no real title available?)
• scientific article; zbMATH DE number 3551720 (Why is no real title available?)
• scientific article; zbMATH DE number 1223843 (Why is no real title available?)
• scientific article; zbMATH DE number 2221907 (Why is no real title available?)
• scientific article; zbMATH DE number 3054843 (Why is no real title available?)
• A new metric for probability distributions
• A stochastic collocation approach to Bayesian inference in inverse problems
• An overview of robust Bayesian analysis. (With discussion)
• Asymptotic Statistics
• Asymptotic coupling and a general form of Harris' theorem with applications to stochastic delay equations
• Brittleness of Bayesian inference and new Selberg formulas
• Brittleness of Bayesian inference under finite information in a continuous world
• Gaussian measures in Banach spaces
• Hierarchical Bayesian level set inversion
• Inverse problems: a Bayesian perspective
• Laplace's method revisited: Weak convergence of probability measures
• Local sensitivity diagnostics for Bayesian inference
• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• On Choosing and Bounding Probability Metrics
• On a Formula for the L2 Wasserstein Metric between Measures on Euclidean and Hilbert Spaces
• On the Bernstein-von Mises phenomenon for nonparametric Bayes procedures
• On the Bernstein-von Mises phenomenon in the Gaussian white noise model
• On the Bernstein-von Mises theorem with infinite-dimensional parameters
• On the brittleness of Bayesian inference
• On the consistency of Bayes estimates
• Optimal Transport
• Perturbation bounds for Monte Carlo within metropolis via restricted approximations
• Perturbation theory for Markov chains via Wasserstein distance
• Posterior consistency for Gaussian process approximations of Bayesian posterior distributions
• Robust Bayesian analysis
• Robust Bayesian analysis using divergence measures
• Robust Bayesian analysis: sensitivity to the prior
• Statistical and computational inverse problems.
• The Bernstein-von Mises theorem under misspecification
• The dilation phenomenon in robust Bayesian inference. (With discussion)
• Well-Posed Bayesian Inverse Problems: Priors with Exponential Tails
• Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
• Well-posed Bayesian inverse problems with infinitely divisible and heavy-tailed prior measures
• Whittle-Matérn priors for Bayesian statistical inversion with applications in electrical impedance tomography

Cited in

(24)

• Wasserstein sensitivity of risk and uncertainty propagation
• On global normal linear approximations for nonlinear Bayesian inverse problems
• Stability of doubly-intractable distributions
• On the well-posedness of Bayesian inverse problems
• Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: a review
• Spectral gaps and error estimates for infinite-dimensional Metropolis-Hastings with non-Gaussian priors
• A MCMC method based on surrogate model and Gaussian process parameterization for infinite Bayesian PDE inversion
• NF-ULA: normalizing flow-based unadjusted Langevin algorithm for imaging inverse problems
• On Bayesian data assimilation for PDEs with ill-posed forward problems
• Error bounds for some approximate posterior measures in Bayesian inference
• Γ -convergence of Onsager–Machlup functionals: I. With applications to maximum a posteriori estimation in Bayesian inverse problems
• A Bayesian scheme for reconstructing obstacles in acoustic waveguides
• Stability estimates for the expected utility in Bayesian optimal experimental design
• Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
• Choosing observation operators to mitigate model error in Bayesian inverse problems
• Markov chain generative adversarial neural networks for solving Bayesian inverse problems in physics applications
• Brittleness of Bayesian inference under finite information in a continuous world
• Optimal experimental design: formulations and computations
• Bayesian Inverse Problems Are Usually Well-Posed
• Image Denoising: The Deep Learning Revolution and Beyond—A Survey Paper
• Analysis of a Computational Framework for Bayesian Inverse Problems: Ensemble Kalman Updates and MAP Estimators under Mesh Refinement
• Lipschitz continuity of probability kernels in the optimal transport framework
• Learning from small data sets: patch-based regularizers in inverse problems for image reconstruction
• Robustness and exploration of variational and machine learning approaches to inverse problems: an overview

This page was built for publication: On the local Lipschitz stability of Bayesian inverse problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5000612)