Convergence rate and concentration inequalities for Gibbs sampling in high dimension
From MaRDI portal
Publication:470046
DOI10.3150/13-BEJ537zbMATH Open1385.60042arXiv1410.4329MaRDI QIDQ470046FDOQ470046
Authors: Neng-Yi Wang, Liming Wu 
Publication date: 11 November 2014
Published in: Bernoulli (Search for Journal in Brave)
Abstract: The objective of this paper is to study the Gibbs sampling for computing the mean of observable in very high dimension - a powerful Markov chain Monte Carlo method. Under the Dobrushin's uniqueness condition, we establish some explicit and sharp estimate of the exponential convergence rate and prove some Gaussian concentration inequalities for the empirical mean.
Full work available at URL: https://arxiv.org/abs/1410.4329
Recommendations
- scientific article; zbMATH DE number 1191611
- Convergence rate of Gibbs sampler and its application
- On convergence rates of Gibbs samplers for uniform distributions
- Rates of convergence for Gibbs sampling for variance component models
- Rate of convergence of the Gibbs sampler in the Gaussian case
- Rates of convergence for Gibbs sampling in the analysis of almost exchangeable data
- Convergence rates for a hierarchical Gibbs sampler
Markov chain Monte Carloconcentration inequalityGibbs measurecoupling methodDobrushin's uniqueness condition
Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Inequalities; stochastic orderings (60E15)
Cites Work
- Sequential Monte Carlo Methods in Practice
- Markov chains and stochastic stability
- General state space Markov chains and MCMC algorithms
- The concentration of measure phenomenon
- Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
- Inégalités de Hoeffding pour les fonctions lipschitziennes de suites dépendantes
- Title not available (Why is that?)
- Bounding \(\bar d\)-distance by informational divergence: A method to prove measure concentration
- A large deviation approach to some transportation cost inequalities
- Title not available (Why is that?)
- Prescribing a System of Random Variables by Conditional Distributions
- Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
- Exponential integrability and transportation cost related to logarithmic Sobolev inequalities
- Dobrushin uniqueness theorem and logarithmic Sobolev inequalities
- Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
- Transportation cost for Gaussian and other product measures
- Title not available (Why is that?)
- Curvature, concentration and error estimates for Markov chain Monte Carlo
- Approach to equilibrium of Glauber dynamics in the one phase region. I: The attractive case
- Title not available (Why is that?)
- A measure concentration inequality for contracting Markov chains
- Title not available (Why is that?)
- Quantitative convergence rates of Markov chains: A simple account
- Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
- Measure concentration and strong mixing
- Transport Inequalities. A Survey
- Gibbs sampling, exponential families and orthogonal polynomials
- Measure concentration for Euclidean distance in the case of dependent random variables.
- Gibbs sampling, conjugate priors and coupling
- Title not available (Why is that?)
- Poincaré and transportation inequalities for Gibbs measures under the Dobrushin uniqueness condition
- Weak transport inequalities and applications to exponential and oracle inequalities
Cited In (13)
- Convergence rates of the blocked Gibbs sampler with random scan in the Wasserstein metric
- Strong replica symmetry for high-dimensional disordered log-concave Gibbs measures
- Convergence rates of Gibbs measures with degenerate minimum
- Concentration inequalities for Gibbs sampling under \(d_{l_{2}}\)-metric
- Title not available (Why is that?)
- Functional central limit theorems for the Gibbs sampler
- Convergence rates of symmetric scan Gibbs sampler
- Rates of convergence for Gibbs sampling in the analysis of almost exchangeable data
- Convergence rate of Gibbs sampler and its application
- Estimating drift and minorization coefficients for Gibbs sampling algorithms
- Comparison theorems for Gibbs measures
- On rates of convergence of stochastic relaxation for Gaussian and non- Gaussian distributions
- Spectral telescope: convergence rate bounds for random-scan Gibbs samplers based on a hierarchical structure
This page was built for publication: Convergence rate and concentration inequalities for Gibbs sampling in high dimension
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q470046)
