Convergence in the Wasserstein Metric for Markov Chain Monte Carlo Algorithms with Applications to Image Restoration

DOI10.1081/STM-200033117zbMath1062.60070WikidataQ113092659 ScholiaQ113092659MaRDI QIDQ3157863

Alison L. Gibbs

Publication date: 19 January 2005

Published in: Stochastic Models (Search for Journal in Brave)

zbMATH Keywords

Ising modelGibbs samplerprobability metricscouplingperfect simulationtotal variation distanceBayesian image restoration

Mathematics Subject Classification ID

Random fields; image analysis (62M40) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20)

Related Items

A Polynomial-Time Perfect Sampler for the Q-Ising with a Vertex-Independent Noise, Kalikow-type decomposition for multicolor infinite range particle systems, Convergence rates of the blocked Gibbs sampler with random scan in the Wasserstein metric, Qualitative Robustness in Bayesian Inference, A Gibbs Sampler for a Class of Random Convex Polytopes, Bayesian Inverse Problems Are Usually Well-Posed, Exact convergence analysis for metropolis–hastings independence samplers in Wasserstein distances, Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances, Perturbation theory for Markov chains via Wasserstein distance, A polynomial-time perfect sampler for the \(Q\)-Ising with a vertex-independent noise, Convergence bound in total variation for an image restoration model, Coupling of Brownian motions in Banach spaces, Perfect Simulation for Image Restoration, An upper bound on the convergence time of the Gibbs sampler in Ising models, Convergence rates of symmetric scan Gibbs sampler, On the Well-posedness of Bayesian Inverse Problems, RWRM: residual Wasserstein regularization model for image restoration, Convergence rate bounds for iterative random functions using one-shot coupling, Approximations of geometrically ergodic reversible markov chains, Wasserstein-based methods for convergence complexity analysis of MCMC with applications

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Geometric bounds for eigenvalues of Markov chains
• Strong uniform times and finite random walks
• An interruptible algorithm for perfect sampling via Markov chains
• Approach to equilibrium of Glauber dynamics in the one phase region. I: The attractive case
• Bayesian computation and stochastic systems. With comments and reply.
• Markov chains for exploring posterior distributions. (With discussion)
• Bounding the convergence time of the Gibbs sampler in Bayesian image restoration
• Polynomial-Time Approximation Algorithms for the Ising Model
• Perfect Simulation of Conditionally Specified Models
• Exact Sampling from a Continuous State Space
• Convergence of Slice Sampler Markov Chains
• Possible biases induced by mcmc convergence diagnostics
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• A very simple algorithm for estimating the number of k‐colorings of a low‐degree graph
• Exact sampling with coupled Markov chains and applications to statistical mechanics
• On Exact Simulation of Markov Random Fields Using Coupling from the Past