Discretization-invariant Bayesian inversion and Besov space priors

DOI10.3934/IPI.2009.3.87MaRDI QIDQ2268280zbMATH OpenOpenAlexWikidataFDO

Authors M. Lassas, Eero Saksman, S. Siltanen

Publication date 10 March 2010

Published in Inverse Problems and Imaging (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/0901.4220

zbMATH Keywords

Bayesian inversionBesov spacediscretization invarianceinverse problemreconstructionstatistical inversionwavelet

Mathematics Subject Classification ID

Nontrigonometric harmonic analysis involving wavelets and other special systems (42C40) Applications of functional analysis in probability theory and statistics (46N30) Functional limit theorems; invariance principles (60F17) Bayesian inference (62F15) Probabilistic models, generic numerical methods in probability and statistics (65C20)

Abstract: Bayesian solution of an inverse problem for indirect measurement $M=AU+mathcalE$ is considered, where $U$ is a function on a domain of $R^d$. Here $A$ is a smoothing linear operator and $mathcalE$ is Gaussian white noise. The data is a realization $m_k$ of the random variable $M_k=P_{k}AU+P_{k}mathcalE$, where $P_k$ is a linear, finite dimensional operator related to measurement device. To allow computerized inversion, the unknown is discretized as $U_n=T_{n}U$, where $T_n$ is a finite dimensional projection, leading to the computational measurement model $M_{kn}=P_{k}A{U}_n+P_{k}mathcalE$. Bayes formula gives then the posterior distribution $p{i}_{kn}(u_n|m_{kn})simp{i}_n(u_n)exp(-1/2|m_{kn}-P_{k}A{u}_n{|}_2^2)$ in $R^d$, and the mean $U_{kn}^{CM}:=int{u}_{n}p{i}_{kn}(u_n|m_k)d{u}_n$ is considered as the reconstruction of $U$. We discuss a systematic way of choosing prior distributions $prio{r}_n$ for all $ngeq{n}_0>0$ by achieving them as projections of a distribution in a infinite-dimensional limit case. Such choice of prior distributions is {em discretization-invariant} in the sense that $prio{r}_n$ represent the same {em a priori} information for all $n$ and that the mean $U_{kn}^{CM}$ converges to a limit estimate as $k,noinfty$. Gaussian smoothness priors and wavelet-based Besov space priors are shown to be discretization invariant. In particular, Bayesian inversion in dimension two with $B_{11}^1$ prior is related to penalizing the $el{l}^1$ norm of the wavelet coefficients of $U$.

Recommendations

• Besov priors for Bayesian inverse problems
• Can one use total variation prior for edge-preserving Bayesian inversion?
• Bayesian approach to inverse problems for functions with a variable-index Besov prior
• Sparsity-promoting Bayesian inversion
• Well-Posed Bayesian Inverse Problems: Priors with Exponential Tails

Cited in

(95)

• Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
• Constructing continuous stationary covariances as limits of the second-order stochastic difference equations
• Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
• Rates of contraction of posterior distributions based on \(p\)-exponential priors
• Infinite-dimensional inverse problems with finite measurements
• Nonparametric Bayesian inference for reversible multidimensional diffusions
• Cauchy Markov random field priors for Bayesian inversion
• Bayesian inversion for electrical-impedance tomography in medical imaging using the nonlinear Poisson-Boltzmann equation
• Wavelet-based priors accelerate maximum-a-posteriori optimization in Bayesian inverse problems
• A scalable algorithm for MAP estimators in Bayesian inverse problems with Besov priors
• Regularization with metric double integrals of functions with values in a set of vectors
• On the lifting of deterministic convergence rates for inverse problems with stochastic noise
• Cauchy difference priors for edge-preserving Bayesian inversion
• Oracle-type posterior contraction rates in Bayesian inverse problems
• Bayesian neural network priors for edge-preserving inversion
• Random tree Besov priors -- towards fractal imaging
• Mathematics of electron tomography
• Bayesian approach to inverse problems for functions with a variable-index Besov prior
• Regularized posteriors in linear ill-posed inverse problems
• Diffusion tensor imaging with deterministic error bounds
• Hierarchical models in statistical inverse problems and the Mumford-Shah functional
• Multiresolution parameter choice method for total variation regularized tomography
• Sparsity-promoting Bayesian inversion
• A Bayesian-based approach to improving acoustic Born waveform inversion of seismic data for viscoelastic media
• The Bayesian formulation of EIT: analysis and algorithms
• A Gaussian hypermodel to recover blocky objects
• A Fast and Scalable Method for A-Optimal Design of Experiments for Infinite-dimensional Bayesian Nonlinear Inverse Problems
• Besov priors for Bayesian inverse problems
• An approximate empirical Bayesian method for large-scale linear-Gaussian inverse problems
• Sparsity-promoting and edge-preserving maximum a posteriori estimators in non-parametric Bayesian inverse problems
• Can one use total variation prior for edge-preserving Bayesian inversion?
• Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
• Whittle-Matérn priors for Bayesian statistical inversion with applications in electrical impedance tomography
• Bernstein-von Mises theorems and uncertainty quantification for linear inverse problems
• Data-driven forward discretizations for Bayesian inversion
• Quasi-Monte Carlo Bayesian estimation under Besov priors in elliptic inverse problems
• Semivariogram methods for modeling Whittle-Matérn priors in Bayesian inverse problems
• Joint estimation of Robin coefficient and domain boundary for the Poisson problem
• Γ -convergence of Onsager–Machlup functionals: I. With applications to maximum a posteriori estimation in Bayesian inverse problems
• Γ-convergence of Onsager–Machlup functionals: II. Infinite product measures on Banach spaces
• Material-separating regularizer for multi-energy x-ray tomography
• Prior normalization for certified likelihood-informed subspace detection of Bayesian inverse problems
• A hybrid Gibbs sampler for edge-preserving tomographic reconstruction with uncertain view angles
• Shearlet-based regularization in statistical inverse learning with an application to x-ray tomography
• Bayesian approach for inverse interior scattering problems with limited aperture
• A Bayesian approach to wavelet-based modelling of discontinuous functions applied to inverse problems
• Reconciling Bayesian and perimeter regularization for binary inversion
• Deep neural network expression of posterior expectations in Bayesian PDE inversion
• Modern regularization methods for inverse problems
• Solving inverse problems using data-driven models
• Generalized Modes in Bayesian Inverse Problems
• Two Metropolis--Hastings Algorithms for Posterior Measures with Non-Gaussian Priors in Infinite Dimensions
• Bayesian Probabilistic Numerical Methods
• Well-Posed Bayesian Inverse Problems: Priors with Exponential Tails
• Correlation priors
• Bayesian inverse problems with l₁ priors: a randomize-then-optimize approach
• The influence of numerical error on parameter estimation and uncertainty quantification for advective PDE models
• Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: a review
• Data-free likelihood-informed dimension reduction of Bayesian inverse problems
• Edge-promoting adaptive Bayesian experimental design for X-ray imaging
• Bayesian inversion techniques for stochastic partial differential equations
• Are Minimizers of the Onsager–Machlup Functional Strong Posterior Modes?
• Field Dynamics Inference for Local and Causal Interactions
• Bayesian inversion with α-stable priors
• Uncertainty Quantification of Inclusion Boundaries in the Context of X-Ray Tomography
• Laplace priors and spatial inhomogeneity in Bayesian inverse problems
• Spectral neural operators
• A Bayesian approach for consistent reconstruction of inclusions
• Horseshoe Priors for Edge-Preserving Linear Bayesian Inversion
• Scalable conditional deep inverse Rosenblatt transports using tensor trains and gradient-based dimension reduction
• On unifying randomized methods for inverse problems
• Besov-Laplace priors in density estimation: optimal posterior contraction rates and adaptation
• An Order-Theoretic Perspective on Modes and Maximum A Posteriori Estimation in Bayesian Inverse Problems
• Adaptive inference over Besov spaces in the white noise model using \(p\)-exponential priors
• Certified coordinate selection for high-dimensional Bayesian inversion with Laplace prior
• Multilevel Monte Carlo FEM for elliptic PDEs with Besov random tree priors
• Heavy-tailed Bayesian nonparametric adaptation
• Bayesian inversion with Student's t priors based on Gaussian scale mixtures
• Hyperpriors for Matérn fields with applications in Bayesian inversion
• Uncertainty quantification. Abstracts from the workshop held April 20--25, 2025
• Maximum a posteriori testing in statistical inverse problems
• Wide stable neural networks: sample regularity, functional convergence and Bayesian inverse problems
• Uncertainty quantification for linear inverse problems with Besov prior: a randomize-then-optimize method
• Continuous Gaussian mixture solution for linear Bayesian inversion with application to Laplace priors
• Fast Variational Inference for Bayesian Factor Analysis in Single and Multi-Study Settings
• Besov space regularised waveform inversion via frequency marching
• Fused \(L_{1/2}\) prior for large scale linear inverse problem with Gibbs bouncy particle sampler
• Consistency of variational inference for Besov priors in non-linear inverse problems
• An augmented Lagrangian method with exact multipliers for non-separable composite \ell₀-\ell₂ regularization
• Discrete to continuum limits in Bayesian inverse problems
• Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem
• Bayesian decomposition using Besov priors
• Spatiotemporal Besov Priors for Bayesian Inverse Problems
• Bernstein-von Mises theorems for statistical inverse problems. I: Schrödinger equation
• Frame-constrained total variation regularization for white noise regression

This page was built for publication: Discretization-invariant Bayesian inversion and Besov space priors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2268280)