Posterior Contraction Rates for the Bayesian Approach to Linear Ill-Posed Inverse Problems

Abstract

We consider a Bayesian nonparametric approach to a family of linear inverse problems in a separable Hilbert space setting with Gaussian noise. We assume Gaussian priors, which are conjugate to the model, and present a method of identifying the posterior using its precision operator. Working with the unbounded precision operator enables us to use partial differential equations (PDE) methodology to obtain rates of contraction of the posterior distribution to a Dirac measure centered on the true solution. Our methods assume a relatively weak relation between the prior covariance, noise covariance and forward operator, allowing for a wide range of applications.

References in corpus (3)

• Rates of contraction of posterior distributions based on Gaussian process priors
• Bayesian inference with rescaled Gaussian process priors
• Rates of contraction for posterior distributions in $\bolds{L^r}$-metrics, $\bolds{1\le r\le\infty}$

Cited by in corpus (34)

• MAP Estimators and Their Consistency in Bayesian Nonparametric Inverse Problems
• Bayesian inverse problems with non-conjugate priors
• Posterior Consistency for Bayesian Inverse Problems through Stability and Regression Results
• Quasi-Bayesian analysis of nonparametric instrumental variables models
• Sparsity-promoting and edge-preserving maximum a posteriori estimators in non-parametric Bayesian inverse problems
• Nonparametric statistical inference for drift vector fields of multi-dimensional diffusions
• Bayesian Posterior Contraction Rates for Linear Severely Ill-posed Inverse Problems
• Convergence Rates for Learning Linear Operators from Noisy Data
• Posterior consistency and convergence rates for Bayesian inversion with hypoelliptic operators
• Dimension-Robust MCMC in Bayesian Inverse Problems
• Consistency of Bayesian inference with Gaussian process priors for a parabolic inverse problem
• Bayes procedures for adaptive inference in inverse problems for the white noise model
• Bayesian linear inverse problems in regularity scales
• Bayesian inverse problems with non-commuting operators
• Importance Sampling: Intrinsic Dimension and Computational Cost
• Stein variational gradient descent on infinite-dimensional space and applications to statistical inverse problems
• Bayesian inverse problems with unknown operators
• Posterior Consistency of Semi-Supervised Regression on Graphs
• An operator learning perspective on parameter-to-observable maps
• Non-centered parametric variational Bayes' approach for hierarchical inverse problems of partial differential equations
• Designing truncated priors for direct and inverse Bayesian problems
• Preconditioning the prior to overcome saturation in Bayesian inverse problems
• Consistency of the posterior distribution in generalised linear inverse problems
• Rejoinder to discussions of "Frequentist coverage of adaptive nonparametric Bayesian credible sets"
• Bayesian Inverse Problems with Heterogeneous Variance
• Posterior Consistency via Precision Operators for Bayesian Nonparametric Drift Estimation in SDEs
• Strong maximum a posteriori estimation in Banach spaces with Gaussian priors
• A Functional Hodrick Prescott Filter
• Analysis of the Gibbs sampler for hierarchical inverse problems
• On the optimal choice of the illumination function in photoacoustic tomography
• Estimation of CO${}_2$ flux from targeted satellite observations: a Bayesian approach
• Pointwise Convergence in Probability of General Smoothing Splines
• Some results on contraction rates for Bayesian inverse problems
• Quasi-Bayesian Dual Instrumental Variable Regression