Posterior-Variance-Based Error Quantification for Inverse Problems in Imaging
From MaRDI portal
Abstract: In this work, a method for obtaining pixel-wise error bounds in Bayesian regularization of inverse imaging problems is introduced. The proposed method employs estimates of the posterior variance together with techniques from conformal prediction in order to obtain coverage guarantees for the error bounds, without making any assumption on the underlying data distribution. It is generally applicable to Bayesian regularization approaches, independent, e.g., of the concrete choice of the prior. Furthermore, the coverage guarantees can also be obtained in case only approximate sampling from the posterior is possible. With this in particular, the proposed framework is able to incorporate any learned prior in a black-box manner. Guaranteed coverage without assumptions on the underlying distributions is only achievable since the magnitude of the error bounds is, in general, unknown in advance. Nevertheless, experiments with multiple regularization approaches presented in the paper confirm that in practice, the obtained error bounds are rather tight. For realizing the numerical experiments, also a novel primal-dual Langevin algorithm for sampling from non-smooth distributions is introduced in this work.
Recommendations
- Proximal Langevin sampling with inexact proximal mapping
- Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
- Scalable Bayesian uncertainty quantification in imaging inverse problems via convex optimization
- Maximum-a-posteriori estimation with Bayesian confidence regions
- MCMC-based image reconstruction with uncertainty quantification
Cited in
(5)- Subgradient Langevin methods for sampling from nonsmooth potentials
- Robustness and exploration of variational and machine learning approaches to inverse problems: an overview
- Neural-network-based regularization methods for inverse problems in imaging
- Diffusion at absolute zero: Langevin sampling using successive Moreau envelopes
- Self-supervised conformal prediction for uncertainty quantification in imaging problems
This page was built for publication: Posterior-Variance-Based Error Quantification for Inverse Problems in Imaging
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6421566)
