Quantitative bounds on convergence of time-inhomogeneous Markov chains

被引:66
作者
Douc, R
Moulines, E
Rosenthal, JS
机构
[1] Ecole Polytech, CMAP, F-91128 Palaiseau, France
[2] Ecole Natl Super Telecommun Bretagne, Dept TSI, CNRS, URA 820, F-75634 Paris 13, France
[3] Univ Toronto, Dept Stat, Toronto, ON M5S 3G3, Canada
关键词
convergence rate; coupling; Markov chain Monte Carlo; simulated annealing; f-total variation;
D O I
10.1214/105051604000000620
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Convergence rates of Markov chains have been widely studied in recent years. In particular, quantitative bounds on convergence rates have been studied in various forms by Meyn and Tweedie [Ann. Appl. Probab. 4 (1994) 981-1101], Rosenthal [J. Amer. Statist. Assoc. 90 (1995) 558-566], Roberts and Tweedie [Stochastic Process. Appl. 80 (1999) 211-229], Jones and Hobert [Statist. Sci. 16 (2001) 312-334] and Fort [Ph.D. thesis (2001) Univ. Paris VI]. In this paper, we extend a result of Rosenthal [J. Amer Statist. Assoc. 90 (1995) 558-566] that concerns quantitative convergence rates for time-homogeneous Markov chains. Our extension allows us to consider f-total variation distance (instead of total variation) and time-inhomogeneous Markov chains. We apply our results to simulated annealing.
引用
收藏
页码:1643 / 1665
页数:23
相关论文
共 20 条
  • [1] Convergence of simulated annealing using Foster-Lyapunov criteria
    Andrieu, C
    Breyer, LA
    Doucet, A
    [J]. JOURNAL OF APPLIED PROBABILITY, 2001, 38 (04) : 975 - 994
  • [2] Barndorff-Nielsen O. E., 1989, Technical report, DOI [DOI 10.1007/978-1-4899-3424-6, 10.1007/978-1-4899-3424-6]
  • [3] BICKEL P, 2001, UNPUB ERGODICITY CON
  • [4] DOUKHAN P, 1980, CR ACAD SCI A MATH, V290, P921
  • [5] FORT G, 2001, THESIS U PARIS 6
  • [6] Stochastic optimization: a review
    Fouskakis, D
    Draper, D
    [J]. INTERNATIONAL STATISTICAL REVIEW, 2002, 70 (03) : 315 - 349
  • [7] An adaptive Metropolis algorithm
    Haario, H
    Saksman, E
    Tamminen, J
    [J]. BERNOULLI, 2001, 7 (02) : 223 - 242
  • [8] HASTINGS WK, 1970, BIOMETRIKA, V57, P97, DOI 10.1093/biomet/57.1.97
  • [9] Honest exploration of intractable probability distributions via Markov chain Monte Carlo
    Jones, GL
    Hobert, JP
    [J]. STATISTICAL SCIENCE, 2001, 16 (04) : 312 - 334
  • [10] Locatelli M, 2002, NONCON OPTIM ITS APP, V62, P179