Bayesian linear inverse problems in regularity scales

DOI10.1214/19-AIHP1029zbMATH Open1460.62059arXiv1802.08992OpenAlexW3098914611MaRDI QIDQ2227478FDOQ2227478

Authors: Shota Gugushvili, Dong Yan, Aad van der Vaart 

Publication date: 15 February 2021

Published in: Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Abstract: We obtain rates of contraction of posterior distributions in inverse problems defined by scales of smoothness classes. We derive abstract results for general priors, with contraction rates determined by Galerkin approximation. The rate depends on the amount of prior concentration near the true function and the prior mass of functions with inferior Galerkin approximation. We apply the general result to non-conjugate series priors, showing that these priors give near optimal and adaptive recovery in some generality, Gaussian priors, and mixtures of Gaussian priors, where the latter are also shown to be near optimal and adaptive. The proofs are based on general testing and approximation arguments, without explicit calculations on the posterior distribution. We are thus not restricted to priors based on the singular value decomposition of the operator. We illustrate the results with examples of inverse problems resulting from differential equations.

Full work available at URL: https://arxiv.org/abs/1802.08992

Recommendations

• Posterior contraction rates for the Bayesian approach to linear ill-posed inverse problems
• Bayesian inverse problems with non-conjugate priors
• Bayesian posterior contraction rates for linear severely ill-posed inverse problems
• Bayesian inverse problems with Gaussian priors
• A general approach to posterior contraction in nonparametric inverse problems

zbMATH Keywords

adaptive estimationlinear inverse problemwhite noiseGaussian priornonparametric Bayesian estimationposterior contraction rateHilbert scaleregularity scalerandom series prior

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Inverse problems for PDEs (35R30) White noise theory (60H40)

Cites Work

• Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition
• Title not available (Why is that?)
• Fundamentals of nonparametric Bayesian inference
• Convergence rates of posterior distributions for non iid observations
• Convergence rates of posterior distributions.
• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• Asymptotic equivalence of nonparametric regression and white noise
• A general approach to posterior contraction in nonparametric inverse problems
• Nonparametric Bayesian model selection and averaging
• Posterior contraction rates for the Bayesian approach to linear ill-posed inverse problems
• Inverse problems: a Bayesian perspective
• Unbounded self-adjoint operators on Hilbert space
• Bayesian inverse problems with non-conjugate priors
• Title not available (Why is that?)
• Title not available (Why is that?)
• Spectral Methods
• Title not available (Why is that?)
• Bayesian inverse problems with Gaussian priors
• Sharp adaptation for inverse problems with random noise
• Empirical Bayes scaling of Gaussian priors in the white noise model
• Bayes procedures for adaptive inference in inverse problems for the white noise model
• Bayesian optimal adaptive estimation using a sieve prior
• Nonparametric statistical inverse problems
• Bayesian recovery of the initial condition for the heat equation
• Rates of contraction of posterior distributions based on Gaussian process priors
• Distributions and Operators
• Practical Approximate Solutions to Linear Operator Equations When the Data are Noisy
• Title not available (Why is that?)
• Function spaces and wavelets on domains
• Distributions, Sobolev spaces, elliptic equations
• Reconstruction from Radon projections and orthogonal expansion on a ball
• An introduction to the mathematical theory of inverse problems
• s-Numbers of operators in Banach spaces
• Adaptive Wavelet Galerkin Methods for Linear Inverse Problems
• Speed of estimation in positron emission tomography and related inverse problems
• Nonparametric Bayesian posterior contraction rates for discretely observed scalar diffusions
• When Do Sobolev Spaces Form a Hilbert Scale?
• Statistical Inverse Estimation in Hilbert Scales
• Convergence Rates of General Regularization Methods for Statistical Inverse Problems and Applications
• SCALES OF BANACH SPACES
• Optimal discretization of inverse problems in Hilbert scales. Regularization and self-regulari\-za\-tion of projection methods
• Variable hilbert scales and their interpolation inequalities with applications to tikhonov regularization
• The Gaussian measure of shifted balls
• Metric entropy and the small ball problem for Gaussian measures
• Approximation and Reconstruction from Attenuated Radon Projections
• Regularizing priors for linear inverse problems
• Adaptive estimation of linear functionals in Hilbert scales from indirect white noise observa\-tions
• On adaptive inverse estimation of linear functional in Hilbert scales
• Error bounds for tikhonov regularization in hilbert scales
• Efficient nonparametric Bayesian inference for \(X\)-ray transforms
• Title not available (Why is that?)
• Inequalities between entropy and approximation numbers of compact maps
• Statistical approach to some ill-posed problems for linear partial differential equations
• Operator theoretic treatment of linear Abel integral equations of first kind
• Functional analysis. An elementary introduction
• Bayesian inverse problems with unknown operators

Cited In (22)

• An informative prior distribution on functions with application to functional regression
• Bayesian inverse problems with non-conjugate priors
• An approximate empirical Bayesian method for large-scale linear-Gaussian inverse problems
• Designing truncated priors for direct and inverse Bayesian problems
• Posterior contraction in Bayesian inverse problems under Gaussian priors
• Bayesian recovery of the initial condition for the heat equation
• Bayesian posterior contraction rates for linear severely ill-posed inverse problems
• Optimal parameter estimation for linear SPDEs from multiple measurements
• Posterior contraction rates for the Bayesian approach to linear ill-posed inverse problems
• Title not available (Why is that?)
• Nonlinear Tikhonov regularization in Hilbert scales for inverse learning
• Title not available (Why is that?)
• Posterior consistency for Bayesian inverse problems through stability and regression results
• Regularized posteriors in linear ill-posed inverse problems
• Bayesian linear inverse problems in regularity scales with discrete observations
• Bayesian inversion techniques for stochastic partial differential equations
• Statistical guarantees for Bayesian uncertainty quantification in nonlinear inverse problems with Gaussian process priors
• Convergence Rates for Learning Linear Operators from Noisy Data
• Convergence results for the Bayesian inversion theory
• Inverse learning in Hilbert scales
• Bayesian inverse problems with unknown operators
• Regularizing priors for linear inverse problems

This page was built for publication: Bayesian linear inverse problems in regularity scales

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2227478)