Bayesian posterior contraction rates for linear severely ill-posed inverse problems

DOI10.1515/JIP-2012-0071zbMATH Open1288.62036arXiv1210.1563OpenAlexW2075682935MaRDI QIDQ2016479FDOQ2016479

Authors: Sergios Agapiou, A. M. Stuart, Yuan-Xiang Zhang 

Publication date: 20 June 2014

Published in: Journal of Inverse and Ill-posed Problems (Search for Journal in Brave)

Abstract: We consider a class of linear ill-posed inverse problems arising from inversion of a compact operator with singular values which decay exponentially to zero. We adopt a Bayesian approach, assuming a Gaussian prior on the unknown function. If the observational noise is assumed to be Gaussian then this prior is conjugate to the likelihood so that the posterior distribution is also Gaussian. We study Bayesian posterior consistency in the small observational noise limit. We assume that the forward operator and the prior and noise covariance operators commute with one another. We show how, for given smoothness assumptions on the truth, the scale parameter of the prior can be adjusted to optimize the rate of posterior contraction to the truth, and we explicitly compute the logarithmic rate.

Full work available at URL: https://arxiv.org/abs/1210.1563

Recommendations

• Posterior contraction rates for the Bayesian approach to linear ill-posed inverse problems
• Bayesian inverse problems with non-conjugate priors
• Bayesian linear inverse problems in regularity scales
• Posterior contraction in Bayesian inverse problems under Gaussian priors
• Bayesian inverse problems with partial observations

zbMATH Keywords

posterior consistencyrate of contractionGaussian priors

Mathematics Subject Classification ID

Bayesian inference (62F15) Applications of functional analysis in probability theory and statistics (46N30) Inverse problems for PDEs (35R30) Inverse problems for integral equations (45Q05) Applications of operator theory in probability theory and statistics (47N30)

Cited In (28)

• A posterior contraction for Bayesian inverse problems in Banach spaces
• Sparsity-promoting and edge-preserving maximum a posteriori estimators in non-parametric Bayesian inverse problems
• Oracle-type posterior contraction rates in Bayesian inverse problems
• Bayesian inverse problems with non-conjugate priors
• Bayesian inverse problems with non-commuting operators
• On the well-posedness of Bayesian inverse problems
• Probabilistic regularization of Fredholm integral equations of the first kind
• Hyperparameter estimation in Bayesian MAP estimation: parameterizations and consistency
• Weak-norm posterior contraction rate of the 4DVAR method for linear severely ill-posed problems
• Importance sampling: intrinsic dimension and computational cost
• Convergence Rates for Linear Inverse Problems in the Presence of an Additive Normal Noise
• A general approach to posterior contraction in nonparametric inverse problems
• Designing truncated priors for direct and inverse Bayesian problems
• Posterior contraction in Bayesian inverse problems under Gaussian priors
• Posterior contraction for empirical Bayesian approach to inverse problems under non-diagonal assumption
• Bayesian Inverse Problems Are Usually Well-Posed
• Posterior contraction rates for the Bayesian approach to linear ill-posed inverse problems
• Posterior consistency and convergence rates for Bayesian inversion with hypoelliptic operators
• Posterior consistency for Bayesian inverse problems through stability and regression results
• Regularized posteriors in linear ill-posed inverse problems
• Bayesian inversion techniques for stochastic partial differential equations
• Bernstein-von Mises theorems and uncertainty quantification for linear inverse problems
• Convergence Rates for Learning Linear Operators from Noisy Data
• An improved quasi-reversibility method for a terminal-boundary value multi-species model with white Gaussian noise
• Bayesian linear inverse problems in regularity scales
• Solving inverse problems using data-driven models
• Analysis of a quasi-reversibility method for nonlinear parabolic equations with uncertainty data
• Bayesian inverse problems with unknown operators

This page was built for publication: Bayesian posterior contraction rates for linear severely ill-posed inverse problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2016479)