Electronic Communications in Probability

Convergence rates of the random scan Gibbs sampler under the Dobrushin’s uniqueness condition

Neng-Yi Wang

Full-text: Open access

Abstract

In this paper, under the Dobrushin’s uniqueness condition, we obtain explicit estimates of the geometrical convergence rate for the random scan Gibbs sampler in the Wasserstein metric.

Article information

Source
Electron. Commun. Probab., Volume 22 (2017), paper no. 56, 7 pp.

Dates
Received: 15 May 2017
Accepted: 25 September 2017
First available in Project Euclid: 13 October 2017

Permanent link to this document
https://projecteuclid.org/euclid.ecp/1507860213

Digital Object Identifier
doi:10.1214/17-ECP90

Mathematical Reviews number (MathSciNet)
MR3718706

Zentralblatt MATH identifier
1378.60015

Subjects
Primary: 60E15: Inequalities; stochastic orderings 65C05: Monte Carlo methods

Keywords
random scan Gibbs sampler coupling method Wasserstein metric Dobrushin’s uniqueness condition

Rights
Creative Commons Attribution 4.0 International License.

Citation

Wang, Neng-Yi. Convergence rates of the random scan Gibbs sampler under the Dobrushin’s uniqueness condition. Electron. Commun. Probab. 22 (2017), paper no. 56, 7 pp. doi:10.1214/17-ECP90. https://projecteuclid.org/euclid.ecp/1507860213


Export citation

References

  • [1] Dobrushin, R. L.: The description of a random field by means of conditional probabilities and condition of its regularity. Theory Probab. Appl., 13(2): 197–224, 1968.
  • [2] Dobrushin, R. L.: Prescribing a system of random variables by conditional distributions. Theory Probab. Appl., 15(3): 458–486, 1970.
  • [3] Marton, K.: Measure concentration for Euclidean distance in the case of dependent random variables. Ann. Probab., 32(3B): 2526–2544, 2004.
  • [4] Roberts, Gareth O. and Rosenthal, Jeffrey S.: General state space Markov chains and MCMC algorithms. Probability Surveys, 1: 20–71, 2004.
  • [5] Villani, C.: Topics in Optimal Transportation. Graduate Studies in Mathematics 58. American Mathematical Society, Providence RI, 2003.
  • [6] Wang, N.-Y. and Wu, L.: Convergence rate and concentration inequalities for Gibbs sampling in high dimension. Bernoulli, 20(4): 1698–1716, 2014.