Low-rank independence samplers in hierarchical Bayesian inverse problems
From MaRDI portal
Publication:4689166
DOI10.1137/17M1137218zbMATH Open1401.65040arXiv1609.07180OpenAlexW2883157112WikidataQ129495354 ScholiaQ129495354MaRDI QIDQ4689166FDOQ4689166
Authors: D. Andrew Brown, Arvind K. Saibaba, Sarah Vallélian 
Publication date: 15 October 2018
Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)
Abstract: In Bayesian inverse problems, the posterior distribution is used to quantify uncertainty about the reconstructed solution. In practice, Markov chain Monte Carlo algorithms often are used to draw samples from the posterior distribution. However, implementations of such algorithms can be computationally expensive. We present a computationally efficient scheme for sampling high-dimensional Gaussian distributions in ill-posed Bayesian linear inverse problems. Our approach uses Metropolis-Hastings independence sampling with a proposal distribution based on a low-rank approximation of the prior-preconditioned Hessian. We show the dependence of the acceptance rate on the number of eigenvalues retained and discuss conditions under which the acceptance rate is high. We demonstrate our proposed sampler by using it with Metropolis-Hastings-within-Gibbs sampling in numerical experiments in image deblurring, computerized tomography, and NMR relaxometry.
Full work available at URL: https://arxiv.org/abs/1609.07180
Recommendations
- Fast Gibbs sampling for high-dimensional Bayesian inversion
- Fast Markov chain Monte Carlo sampling for sparse Bayesian inference in high-dimensional inverse problems using L1-type priors
- Dimension-independent likelihood-informed MCMC
- Optimal low-rank approximations of Bayesian linear inverse problems
- A Metropolis-Hastings-within-Gibbs sampler for nonlinear hierarchical-Bayesian inverse problems
low-rank approximationimage deblurringcomputerized tomographyMetropolis-Hastings independence samplerprior-preconditioned Hessian
Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40) Ill-posedness and regularization problems in numerical linear algebra (65F22)
Cites Work
- Regularization tools version \(4.0\) for matlab \(7.3\)
- Gaussian Markov Random Fields
- Inference from iterative simulation using multiple sequences
- Bayesian data analysis.
- The design and analysis of computer experiments.
- Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
- Gaussian processes for machine learning.
- Covariance structure of the Gibbs sampler with applications to the comparisons of estimators and augmentation schemes
- Title not available (Why is that?)
- Statistical and computational inverse problems.
- Sampling-Based Approaches to Calculating Marginal Densities
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
- A general framework for the parametrization of hierarchical models
- Monte Carlo sampling methods using Markov chains and their applications
- Title not available (Why is that?)
- Prior distributions for variance parameters in hierarchical models (Comment on article by Browne and Draper)
- Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
- Applied multivariate statistical analysis.
- Statistical decision theory and Bayesian analysis. 2nd ed
- An exploration of aspects of Bayesian multiple testing
- Partially Collapsed Gibbs Samplers
- Equation of state calculations by fast computing machines
- Inverse problems: a Bayesian perspective
- Numerical methods for large eigenvalue problems
- Bayesian methods for data analysis.
- Title not available (Why is that?)
- Analysis of the Gibbs Sampler for Hierarchical Inverse Problems
- Optimal proposal distributions and adaptive MCMC
- An introduction to variational methods for graphical models
- Discrete inverse problems. Insight and algorithms.
- A computational framework for infinite-dimensional Bayesian inverse problems. I: The linearized case, with application to global seismic inversion
- Title not available (Why is that?)
- Fast algorithms for Bayesian uncertainty quantification in large-scale linear inverse problems based on low-rank partial Hessian approximations
- Title not available (Why is that?)
- A computational framework for infinite-dimensional Bayesian inverse problems. II: stochastic Newton MCMC with application to ice sheet flow inverse problems
- MCMC-based image reconstruction with uncertainty quantification
- Point spread function estimation in X-ray imaging with partially collapsed Gibbs sampling
- Component-wise Markov chain Monte Carlo: uniform and geometric ergodicity under mixing and composition
- Bayesian Inversion of Geoelectrical Resistivity Data
- Inverse problems in the Bayesian framework
- Optimal low-rank approximations of Bayesian linear inverse problems
- Randomized algorithms for generalized Hermitian eigenvalue problems with application to computing Karhunen-Loève expansion.
- Fast sampling in a linear-Gaussian inverse problem
- Practical sketching algorithms for low-rank matrix approximation
- Applications of a nonnegatively constrained iterative method with statistically based stopping rules to CT, PET, and SPECT imaging
- Efficient MCMC-based image deblurring with Neumann boundary conditions
- A METROPOLIS-HASTINGS METHOD FOR LINEAR INVERSE PROBLEMS WITH POISSON LIKELIHOOD AND GAUSSIAN PRIOR
- A Bayesian generalized CAR model for correlated signal detection
Cited In (20)
- Randomized approaches to accelerate MCMC algorithms for Bayesian inverse problems
- Some rapidly mixing hit-and-run samplers for latent counts in linear inverse problems
- Solving large-scale PDE-constrained Bayesian inverse problems with Riemann manifold Hamiltonian Monte Carlo
- A Metropolis-Hastings-within-Gibbs sampler for nonlinear hierarchical-Bayesian inverse problems
- Certified coordinate selection for high-dimensional Bayesian inversion with Laplace prior
- Hybrid samplers for ill-posed inverse problems
- Fast Gibbs sampling for high-dimensional Bayesian inversion
- Low-rank tensor reconstruction of concentrated densities with application to Bayesian inversion
- Sampling-free Bayesian inversion with adaptive hierarchical tensor representations
- Implicit sampling for hierarchical Bayesian inversion and applications in fractional multiscale diffusion models
- Computationally efficient sampling methods for sparsity promoting hierarchical Bayesian models
- Localization for MCMC: sampling high-dimensional posterior distributions with local structure
- Fast Markov chain Monte Carlo sampling for sparse Bayesian inference in high-dimensional inverse problems using L1-type priors
- Analysis of the Gibbs Sampler for Hierarchical Inverse Problems
- A computational framework for infinite-dimensional Bayesian inverse problems. II: stochastic Newton MCMC with application to ice sheet flow inverse problems
- Efficient Marginalization-Based MCMC Methods for Hierarchical Bayesian Inverse Problems
- Dimension-Independent MCMC Sampling for Inverse Problems with Non-Gaussian Priors
- A Gaussian Process Emulator Based Approach for Bayesian Calibration of a Functional Input
- Efficient nonparametric Bayesian inference for \(X\)-ray transforms
- Fast sampling in a linear-Gaussian inverse problem
Uses Software
This page was built for publication: Low-rank independence samplers in hierarchical Bayesian inverse problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4689166)
