Open Access
November 2014 Convergence rate and concentration inequalities for Gibbs sampling in high dimension
Neng-Yi Wang, Liming Wu
Bernoulli 20(4): 1698-1716 (November 2014). DOI: 10.3150/13-BEJ537


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.


Download Citation

Neng-Yi Wang. Liming Wu. "Convergence rate and concentration inequalities for Gibbs sampling in high dimension." Bernoulli 20 (4) 1698 - 1716, November 2014.


Published: November 2014
First available in Project Euclid: 19 September 2014

zbMATH: 06368414
MathSciNet: MR3263086
Digital Object Identifier: 10.3150/13-BEJ537

Keywords: concentration inequality , Coupling method , Dobrushin’s uniqueness condition , Gibbs measure , Markov chain Monte Carlo

Rights: Copyright © 2014 Bernoulli Society for Mathematical Statistics and Probability

Vol.20 • No. 4 • November 2014
Back to Top