Convergence rate and concentration inequalities for Gibbs sampling in high dimension

DOI10.3150/13-BEJ537zbMath1385.60042arXiv1410.4329MaRDI QIDQ470046

Neng-Yi Wang, Li-ming Wu

Publication date: 11 November 2014

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1410.4329

zbMATH Keywords

Markov chain Monte CarloGibbs measureconcentration inequalitycoupling methodDobrushin's uniqueness condition

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Inequalities; stochastic orderings (60E15) Monte Carlo methods (65C05)

Related Items (3)

Convergence rates of the blocked Gibbs sampler with random scan in the Wasserstein metric ⋮ Spectral telescope: convergence rate bounds for random-scan Gibbs samplers based on a hierarchical structure ⋮ Convergence rates of symmetric scan Gibbs sampler

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Curvature, concentration and error estimates for Markov chain Monte Carlo
• Markov chains and stochastic stability
• Poincaré and transportation inequalities for Gibbs measures under the Dobrushin uniqueness condition
• Weak transport inequalities and applications to exponential and oracle inequalities
• Gibbs sampling, exponential families and orthogonal polynomials
• General state space Markov chains and MCMC algorithms
• Dobrushin uniqueness theorem and logarithmic Sobolev inequalities
• Exponential integrability and transportation cost related to logarithmic Sobolev inequalities
• Approach to equilibrium of Glauber dynamics in the one phase region. I: The attractive case
• Quantitative convergence rates of Markov chains: A simple account
• Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
• Measure concentration for Euclidean distance in the case of dependent random variables.
• Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
• A measure concentration inequality for contracting Markov chains
• Transportation cost for Gaussian and other product measures
• Gibbs sampling, conjugate priors and coupling
• Bounding \(\bar d\)-distance by informational divergence: A method to prove measure concentration
• A large deviation approach to some transportation cost inequalities
• Sequential Monte Carlo Methods in Practice
• Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
• Measure concentration and strong mixing
• Inégalités de Hoeffding pour les fonctions lipschitziennes de suites dépendantes
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• Transport Inequalities. A Survey
• Prescribing a System of Random Variables by Conditional Distributions

This page was built for publication: Convergence rate and concentration inequalities for Gibbs sampling in high dimension