Fluctuations of interacting Markov chain Monte Carlo methods

被引：3
|
作者：
Bercu, Bernard [2 ,3 ]
Del Moral, Pierre [2 ,3 ,4 ]
Doucet, Arnaud [1 ]
机构：
[1] Univ Oxford, Dept Stat, Oxford OX1 3TG, England
[2] Univ Bordeaux, Ctr INRIA Bordeaux Sud Ouest, F-33405 Talence, France
[3] Univ Bordeaux, Inst Math Bordeaux, F-33405 Talence, France
[4] Ctr Appl Math, F-9112 Palaiseau, France
来源：
STOCHASTIC PROCESSES AND THEIR APPLICATIONS | 2012年 / 122卷 / 04期
关键词：
Multivariate central limit theorems; Random fields; Martingale limit theorems; Self-interacting Markov chains; Markov chain Monte Carlo algorithms; ERGODICITY;
D O I：
10.1016/j.spa.2012.01.001
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：
We present a multivariate central limit theorem for a general class of interacting Markov chain Monte Carlo algorithms used to solve nonlinear measure-valued equations. These algorithms generate stochastic processes which belong to the class of nonlinear Markov chains interacting with their empirical occupation measures. We develop an original theoretical analysis based on resolvent operators and semigroup techniques to analyze the fluctuations of their occupation measures around their limiting values. (c) 2012 Elsevier By. All rights reserved.
引用
收藏
页码：1304 / 1331
页数：28
相关论文
共 50 条
  • [1] SEQUENTIALLY INTERACTING MARKOV CHAIN MONTE CARLO METHODS
    Brockwell, Anthony
    Del Moral, Pierre
    Doucet, Arnaud
    ANNALS OF STATISTICS, 2010, 38 (06): : 3387 - 3411
  • [2] A new class of interacting Markov chain Monte Carlo methods
    Del Moral, Pierre
    Doucet, Arnaud
    COMPTES RENDUS MATHEMATIQUE, 2010, 348 (1-2) : 79 - 83
  • [3] Interacting Particle Markov Chain Monte Carlo
    Rainforth, Tom
    Naesseth, Christian A.
    Lindsten, Fredrik
    Paige, Brooks
    van de Meent, Jan-Willem
    Doucet, Arnaud
    Wood, Frank
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 48, 2016, 48
  • [4] Parallel and interacting Markov chain Monte Carlo algorithm
    Campillo, Fabien
    Rakotozafy, Rivo
    Rossi, Vivien
    MATHEMATICS AND COMPUTERS IN SIMULATION, 2009, 79 (12) : 3424 - 3433
  • [5] An introduction to Markov chain Monte Carlo methods
    Besag, J
    MATHEMATICAL FOUNDATIONS OF SPEECH AND LANGUAGE PROCESSING, 2004, 138 : 247 - 270
  • [6] A Functional Central Limit Theorem for a Class of Interacting Markov Chain Monte Carlo Methods
    Bercu, Bernard
    Del Moral, Pierre
    Doucet, Arnaud
    ELECTRONIC JOURNAL OF PROBABILITY, 2009, 14 : 2130 - 2155
  • [7] MARGINAL MARKOV CHAIN MONTE CARLO METHODS
    van Dyk, David A.
    STATISTICA SINICA, 2010, 20 (04) : 1423 - 1454
  • [8] Particle Markov chain Monte Carlo methods
    Andrieu, Christophe
    Doucet, Arnaud
    Holenstein, Roman
    JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2010, 72 : 269 - 342
  • [9] The Evolution of Markov Chain Monte Carlo Methods
    Richey, Matthew
    AMERICAN MATHEMATICAL MONTHLY, 2010, 117 (05): : 383 - 413
  • [10] CONVERGENCE OF ADAPTIVE AND INTERACTING MARKOV CHAIN MONTE CARLO ALGORITHMS
    Fort, G.
    Moulines, E.
    Priouret, P.
    ANNALS OF STATISTICS, 2011, 39 (06): : 3262 - 3289
12345