A PIECEWISE DETERMINISTIC SCALING LIMIT OF LIFTED METROPOLIS-HASTINGS IN THE CURIE WEISS MODEL

被引:45
|
作者
Bierkens, Joris [1 ]
Roberts, Gareth [2 ]
机构
[1] Delft Univ Technol, DIAM EECMS, Mekelweg 4, NL-2628 CD Delft, Netherlands
[2] Univ Warwick, Dept Stat, Coventry CV4 7AL, W Midlands, England
基金
英国工程与自然科学研究理事会;
关键词
Weak convergence; Markov chain Monte Carlo; piecewise deterministic Markov process; phase transition; exponential ergodicity; LONG-TIME BEHAVIOR; VARIANCE REDUCTION; STEINS METHOD;
D O I
10.1214/16-AAP1217
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
In Turitsyn, Chertkov and Vucelja [Phys. D 240 (2011) 410-414] a nonreversible Markov Chain Monte Carlo (MCMC) method on an augmented state space was introduced, here referred to as Lifted Metropolis Hastings (LMH). A scaling limit of the magnetization process in the Curie Weiss model is derived for LMH, as well as for Metropolis Hastings (MH). The required jump rate in the high (supercritical) temperature regime equals n(1/2) for LMH, which should be compared to n for MH. At the critical temperature, the required jump rate equals n(3/4) for LMH and n(3/2) for MH, in agreement with experimental results of Turitsyn, Chertkov and Vucelja (2011). The scaling limit of LMH turns out to be a nonreversible piecewise deterministic exponentially ergodic "zig-zag" Markov process.
引用
收藏
页码:846 / 882
页数:37
相关论文
共 11 条
  • [1] COUNTEREXAMPLES FOR OPTIMAL SCALING OF METROPOLIS-HASTINGS CHAINS WITH ROUGH TARGET DENSITIES
    Vogrinc, Jure
    Kendall, Wilfrid S.
    ANNALS OF APPLIED PROBABILITY, 2021, 31 (02) : 972 - 1019
  • [2] Scaling limits for the transient phase of local Metropolis-Hastings algorithms
    Christensen, OF
    Roberts, GO
    Rosenthal, JS
    JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2005, 67 : 253 - 268
  • [3] Adaptive optimal scaling of Metropolis-Hastings algorithms using the Robbins-Monro process
    Garthwaite, P. H.
    Fan, Y.
    Sisson, S. A.
    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2016, 45 (17) : 5098 - 5111
  • [4] Bayesian analysis of the Logit model and comparison of two Metropolis-Hastings strategies
    Altaleb, A
    Chauveau, D
    COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2002, 39 (02) : 137 - 152
  • [5] Efficient implementation of the Metropolis-Hastings algorithm, with application to the Cormack–Jolly–Seber model
    William A. Link
    Richard J. Barker
    Environmental and Ecological Statistics, 2008, 15 : 79 - 87
  • [6] Efficient implementation of the Metropolis-Hastings algorithm, with application to the Cormack-Jolly-Seber model
    Link, William A.
    Barker, Richard J.
    ENVIRONMENTAL AND ECOLOGICAL STATISTICS, 2008, 15 (01) : 79 - 87
  • [7] Macroscopic Limit of a Bipartite Curie–Weiss Model: A Dynamical Approach
    Francesca Collet
    Journal of Statistical Physics, 2014, 157 : 1301 - 1319
  • [8] Macroscopic Limit of a Bipartite Curie-Weiss Model: A Dynamical Approach
    Collet, Francesca
    JOURNAL OF STATISTICAL PHYSICS, 2014, 157 (06) : 1301 - 1319
  • [9] Bayesian Analysis of Mixture Normal Model via Equi-Energy Sampler and Improved Metropolis-Hastings Algorithm
    Shao, Wei
    Zhao, Guoqing
    Shao, Feifei
    2015 INTERNATIONAL CONFERENCE ON CYBER-ENABLED DISTRIBUTED COMPUTING AND KNOWLEDGE DISCOVERY, 2015, : 306 - 309
  • [10] Bayesian parameter estimation for a jet-milling model using Metropolis-Hastings and Wang-Landau sampling
    Kastner, Catharine A.
    Braumann, Andreas
    Man, Peter L. W.
    Mosbach, Sebastian
    Brownbridge, George P. E.
    Akroyd, Jethro
    Kraft, Markus
    Himawan, Chrismono
    CHEMICAL ENGINEERING SCIENCE, 2013, 89 : 244 - 257