Designing truncated priors for direct and inverse Bayesian problems
From MaRDI portal
Publication:2136605
DOI10.1214/21-EJS1966zbMATH Open1493.62238arXiv2105.10254OpenAlexW3165874090MaRDI QIDQ2136605FDOQ2136605
Publication date: 11 May 2022
Published in: Electronic Journal of Statistics (Search for Journal in Brave)
Abstract: The Bayesian approach to inverse problems with functional unknowns, has received significant attention in recent years. An important component of the developing theory is the study of the asymptotic performance of the posterior distribution in the frequentist setting. The present paper contributes to the area of Bayesian inverse problems by formulating a posterior contraction theory for linear inverse problems, with truncated Gaussian series priors, and under general smoothness assumptions. Emphasis is on the intrinsic role of the truncation point both for the direct as well as for the inverse problem, which are related through the modulus of continuity as this was recently highlighted by Knapik and Salomond (2018).
Full work available at URL: https://arxiv.org/abs/2105.10254
Recommendations
Bayesian inference (62F15) Asymptotic properties of nonparametric inference (62G20) Bayesian problems; characterization of Bayes procedures (62C10) Inverse problems for integral equations (45Q05)
Cites Work
- Title not available (Why is that?)
- Mathematical Foundations of Infinite-Dimensional Statistical Models
- Convergence rates of posterior distributions for non iid observations
- Bernstein-von Mises theorems for statistical inverse problems. I: Schrödinger equation
- A general approach to posterior contraction in nonparametric inverse problems
- Bayesian aspects of some nonparametric problems
- Bayesian posterior contraction rates for linear severely ill-posed inverse problems
- Posterior contraction rates for the Bayesian approach to linear ill-posed inverse problems
- The mathematics of computerized tomography
- Posterior consistency and convergence rates for Bayesian inversion with hypoelliptic operators
- Title not available (Why is that?)
- Bayesian inverse problems with non-conjugate priors
- Geometry of linear ill-posed problems in variable Hilbert scales
- Posterior Contraction in Bayesian Inverse Problems Under Gaussian Priors
- Title not available (Why is that?)
- How general are general source conditions?
- Bayesian inverse problems with Gaussian priors
- Adaptive Bayesian inference on the mean of an infinite-dimensional normal distribution
- Empirical Bayes scaling of Gaussian priors in the white noise model
- Lower bounds for posterior rates with Gaussian process priors
- Bayesian optimal adaptive estimation using a sieve prior
- Bayesian Recovery of the Initial Condition for the Heat Equation
- Rates of contraction of posterior distributions based on Gaussian process priors
- Tikhonov Regularization for Finitely and Infinitely Smoothing Operators
- Minimax risk over hyperrectangles, and implications
- Regularization by projection: Approximation theoretic aspects and distance functions
- Discretization strategy for linear ill-posed problems in variable Hilbert scales
- On statistical Calderón problems
- Interpolation in variable Hilbert scales with application to inverse problems
- Regularization by projection in variable Hilbert scales
- Consistency of Bayesian inference with Gaussian process priors in an elliptic inverse problem
- Tikhonov regularization with oversmoothing penalty for non-linear ill-posed problems in Hilbert scales
- Bayesian inverse problems with non-commuting operators
- Bayesian linear inverse problems in regularity scales
- Minimax rates for statistical inverse problems under general source conditions
Cited In (3)
This page was built for publication: Designing truncated priors for direct and inverse Bayesian problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2136605)
