On the well-posedness of Bayesian inverse problems
From MaRDI portal
Bayesian inferenceinverse problemsKullback-Leibler divergencetotal variationWassersteinwell-posedness
Sensitivity, stability, well-posedness (49K40) Inverse problems in optimal control (49N45) Bayesian inference (62F15) Numerical methods for inverse problems for boundary value problems involving PDEs (65N21) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)
Abstract: The subject of this article is the introduction of a new concept of well-posedness of Bayesian inverse problems. The conventional concept of (Lipschitz, Hellinger) well-posedness in [Stuart 2010, Acta Numerica 19, pp. 451-559] is difficult to verify in practice and may be inappropriate in some contexts. Our concept simply replaces the Lipschitz continuity of the posterior measure in the Hellinger distance by continuity in an appropriate distance between probability measures. Aside from the Hellinger distance, we investigate well-posedness with respect to weak convergence, the total variation distance, the Wasserstein distance, and also the Kullback--Leibler divergence. We demonstrate that the weakening to continuity is tolerable and that the generalisation to other distances is important. The main results of this article are proofs of well-posedness with respect to some of the aforementioned distances for large classes of Bayesian inverse problems. Here, little or no information about the underlying model is necessary; making these results particularly interesting for practitioners using black-box models. We illustrate our findings with numerical examples motivated from machine learning and image processing.
Recommendations
- On the local Lipschitz stability of Bayesian inverse problems
- Well-Posed Bayesian Inverse Problems: Priors with Exponential Tails
- Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
- Well-posed Bayesian inverse problems with infinitely divisible and heavy-tailed prior measures
- Inverse problems: a Bayesian perspective
Cites work
- A Bayesian level set method for geometric inverse problems
- An application of sparse measure valued Bayesian inversion to acoustic sound source identification
- An Inverse Problem for the Steady State Diffusion Equation
- Analysis of the ensemble and polynomial chaos Kalman filters in Bayesian inverse problems
- Asymmetric topologies on statistical manifolds
- Bayesian Parameter Identification in Cahn--Hilliard Models for Biological Growth
- Bayesian posterior contraction rates for linear severely ill-posed inverse problems
- Bayesian Probabilistic Numerical Methods
- Convergence in the Wasserstein Metric for Markov Chain Monte Carlo Algorithms with Applications to Image Restoration
- Fast sampling of parameterised Gaussian random fields
- Hierarchical Bayesian level set inversion
- Higher order quasi-Monte Carlo integration for Bayesian PDE inversion
- How deep are deep Gaussian processes?
- scientific article; zbMATH DE number 1223843 (Why is no real title available?)
- scientific article; zbMATH DE number 1416652 (Why is no real title available?)
- Introduction to uncertainty quantification
- Inverse problems: a Bayesian perspective
- Linear Inverse Problems
- Nonlinear least squares for inverse problems. Theoretical foundations and step-by-step guide for applications
- On Choosing and Bounding Probability Metrics
- On the local Lipschitz stability of Bayesian inverse problems
- Optimal Transport
- Perturbation theory for Markov chains via Wasserstein distance
- Selection, calibration, and validation of models of tumor growth
- Sparse deterministic approximation of Bayesian inverse problems
- Uncertainty Quantification and Weak Approximation of an Elliptic Inverse Problem
- Uncertainty quantification in graph-based classification of high dimensional data
- Well-posed Bayesian geometric inverse problems arising in subsurface flow
- Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
- Well-posed Bayesian inverse problems with infinitely divisible and heavy-tailed prior measures
- Well-Posed Bayesian Inverse Problems: Priors with Exponential Tails
- What is a statistical model? (With comments and rejoinder).
Cited in
(44)- A hierarchical Bayesian setting for an inverse problem in linear parabolic PDEs with noisy boundary conditions
- Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
- Generalized parallel tempering on Bayesian inverse problems
- Deep microlocal reconstruction for limited-angle tomography
- On the convergence of the Laplace approximation and noise-level-robustness of Laplace-based Monte Carlo methods for Bayesian inverse problems
- Stability of doubly-intractable distributions
- A fully Bayesian approach to assessment of model adequacy in inverse problems
- Sparse approximation of triangular transports. I: The finite-dimensional case
- Approximation of Bayesian Inverse Problems for PDEs
- scientific article; zbMATH DE number 168139 (Why is no real title available?)
- Bayesian Inversion by ω-Complete Cone Duality
- Well-posed Bayesian inverse problems with infinitely divisible and heavy-tailed prior measures
- scientific article; zbMATH DE number 1415983 (Why is no real title available?)
- The Bayesian formulation and well-posedness of fractional elliptic inverse problems
- On the local Lipschitz stability of Bayesian inverse problems
- Γ -convergence of Onsager–Machlup functionals: I. With applications to maximum a posteriori estimation in Bayesian inverse problems
- A Bayesian approach to wavelet-based modelling of discontinuous functions applied to inverse problems
- On Bayesian data assimilation for PDEs with ill-posed forward problems
- Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
- Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
- Kernel Methods for Bayesian Elliptic Inverse Problems on Manifolds
- Error bounds for some approximate posterior measures in Bayesian inference
- Stability of Gibbs posteriors from the Wasserstein loss for Bayesian full waveform inversion
- Multilevel adaptive sparse Leja approximations for Bayesian inverse problems
- Generalized Modes in Bayesian Inverse Problems
- Well-Posed Bayesian Inverse Problems: Priors with Exponential Tails
- Posterior consistency for Bayesian inverse problems through stability and regression results
- Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: a review
- The ensemble Kalman filter for rare event estimation
- Bayesian approach for limited-aperture inverse acoustic scattering with total variation prior
- A Bayesian scheme for reconstructing obstacles in acoustic waveguides
- Component-wise iterative ensemble Kalman inversion for static Bayesian models with unknown measurement error covariance
- Bayesian Inverse Problems Are Usually Well-Posed
- Analysis of a Computational Framework for Bayesian Inverse Problems: Ensemble Kalman Updates and MAP Estimators under Mesh Refinement
- On unifying randomized methods for inverse problems
- Lipschitz continuity of probability kernels in the optimal transport framework
- NF-ULA: normalizing flow-based unadjusted Langevin algorithm for imaging inverse problems
- Bayesian inverse problems with Gaussian priors
- Nested sampling for uncertainty quantification and rare event estimation
- Learning from small data sets: patch-based regularizers in inverse problems for image reconstruction
- Elliptic Bayesian inverse problems on metric graphs
- Uncertainty estimation for learning-based classification of corrupted images
- Introduction to Gaussian process regression in Bayesian inverse problems, with new results on experimental design for weighted error measures
- Gaussian measures conditioned on nonlinear observations: consistency, MAP estimators, and simulation
This page was built for publication: On the well-posedness of Bayesian inverse problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4960997)
