Electronic Communications in Probability

Concentration inequalities for Gibbs sampling under $d_{l_{2}}$-metric

Neng-Yi Wang

Full-text: Open access

Abstract

The aim of this paper is to investigate the Gibbs sampling that's used for computing the mean of observables with respect to some function $f$ depending on a very small number of variables. For this type of observable, by using the $d_{l_{2}}$-metric one obtains the sharp concentration estimate for the empirical mean, which in particular yields the correct speed in the concentration for $f$ depending on a single observable.

Article information

Source
Electron. Commun. Probab., Volume 19 (2014), paper no. 63, 11 pp.

Dates
Accepted: 18 September 2014
First available in Project Euclid: 7 June 2016

Permanent link to this document
https://projecteuclid.org/euclid.ecp/1465316765

Digital Object Identifier
doi:10.1214/ECP.v19-3502

Mathematical Reviews number (MathSciNet)
MR3262069

Zentralblatt MATH identifier
1319.60039

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

Keywords
concentration inequality Gibbs sampling coupling method Dobrushin's uniqueness condition $d_{l_2}$-metric

Rights
This work is licensed under a Creative Commons Attribution 3.0 License.

Citation

Wang, Neng-Yi. Concentration inequalities for Gibbs sampling under $d_{l_{2}}$-metric. Electron. Commun. Probab. 19 (2014), paper no. 63, 11 pp. doi:10.1214/ECP.v19-3502. https://projecteuclid.org/euclid.ecp/1465316765


Export citation

References

  • Bobkov, S. G.; Goetze, F. Exponential integrability and transportation cost related to logarithmic Sobolev inequalities. J. Funct. Anal. 163 (1999), no. 1, 1–28.
  • Cattiaux, Patrick; Guillin, Arnaud; Wu, Li-Ming. A note on Talagrand's transportation inequality and logarithmic Sobolev inequality. Probab. Theory Related Fields 148 (2010), no. 1-2, 285–304.
  • Djellout, H.; Guillin, A.; Wu, L. Transportation cost-information inequalities and applications to random dynamical systems and diffusions. Ann. Probab. 32 (2004), no. 3B, 2702–2732.
  • Dobrushin, R. L. Description of a random field by means of conditional probabilities and conditions for its regularity. (Russian) Teor. Verojatnost. i Primenen 13 1968 201–229.
  • Dobrushin, R. L.: Prescribing a system of random variables by conditional distributions. ph Theory Probab. Appl., 15(3): 458-486, 1970.
  • Dyer, Martin; Goldberg, Leslie Ann; Jerrum, Mark. Dobrushin conditions and systematic scan. Combin. Probab. Comput. 17 (2008), no. 6, 761–779.
  • Gozlan, Nathael; Leonard, Christian. A large deviation approach to some transportation cost inequalities. Probab. Theory Related Fields 139 (2007), no. 1-2, 235–283.
  • Gozlan, N.; Leonard, C. Transport inequalities. A survey. Markov Process. Related Fields 16 (2010), no. 4, 635–736.
  • Ledoux, Michel. Concentration of measure and logarithmic Sobolev inequalities. Seminaire de Probabilites, XXXIII, 120–216, Lecture Notes in Math., 1709, Springer, Berlin, 1999.
  • Ledoux, Michel. The concentration of measure phenomenon. Mathematical Surveys and Monographs, 89. American Mathematical Society, Providence, RI, 2001. x+181 pp. ISBN: 0-8218-2864-9
  • Marton, K. Bounding $\overline d$-distance by informational divergence: a method to prove measure concentration. Ann. Probab. 24 (1996), no. 2, 857–866.
  • Marton, K. A measure concentration inequality for contracting Markov chains. Geom. Funct. Anal. 6 (1996), no. 3, 556–571.
  • Marton, Katalin. Measure concentration for Euclidean distance in the case of dependent random variables. Ann. Probab. 32 (2004), no. 3B, 2526–2544.
  • Otto, F.; Villani, C. Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality. J. Funct. Anal. 173 (2000), no. 2, 361–400.
  • Talagrand, M. Transportation cost for Gaussian and other product measures. Geom. Funct. Anal. 6 (1996), no. 3, 587–600.
  • Villani, C. Topics in optimal transportation. Graduate Studies in Mathematics, 58. American Mathematical Society, Providence, RI, 2003. xvi+370 pp. ISBN: 0-8218-3312-X
  • Wang, N.-Y. and Wu, L.: Convergence rate and concentration inequalities for Gibbs sampling in high dimension. To appear in Bernoulli.