Polynomial Convergence Rates of Piecewise Deterministic Markov Processes

被引:0
作者
Roberts, Gareth O. [1 ]
Rosenthal, Jeffrey S. [2 ]
机构
[1] Univ Warwick, Dept Stat, Coventry CV4 7AL, England
[2] Univ Toronto, Dept Stat, Toronto, ON M5S 3G3, Canada
基金
加拿大自然科学与工程研究理事会; 英国工程与自然科学研究理事会;
关键词
PDMP; MCMC; Bouncy Particle sampler; Zig Zag algorithm; Convergence rate; Polynomial convergence; Infinitesimal generator; Drift condition; SUBGEOMETRIC ERGODICITY;
D O I
10.1007/s11009-023-09977-2
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 consider piecewise-deterministic Markov processes such as the Bouncy Particle sampler, on target densities with polynomial tails. Using direct drift condition methods, we provide bounds on the polynomial order of the processes' convergence rate to stationary, on both one-dimensional and high-dimensional state spaces, in both total variation distance and f-norm.
引用
收藏
页数:18
相关论文
共 17 条
[1]   HYPOCOERCIVITY OF PIECEWISE DETERMINISTIC MARKOV PROCESS-MONTE CARLO [J].
Andrieu, Christophe ;
Durmus, Alain ;
Nusken, Nikolas ;
Roussel, Julien .
ANNALS OF APPLIED PROBABILITY, 2021, 31 (05) :2478-2517
[2]   Subgeometric hypocoercivity for piecewise-deterministic Markov process Monte Carlo methods [J].
Andrieu, Christophe ;
Dobson, Paul ;
Wang, Andi Q. .
ELECTRONIC JOURNAL OF PROBABILITY, 2021, 26
[3]  
Bierkens J, 2021, PIECEWISE DETERMINIS
[4]   ERGODICITY OF THE ZIGZAG PROCESS [J].
Bierkens, Joris ;
Roberts, Gareth O. ;
Zitt, Pierre-Andre .
ANNALS OF APPLIED PROBABILITY, 2019, 29 (04) :2266-2301
[5]   The Bouncy Particle Sampler: A Nonreversible Rejection-Free Markov Chain Monte Carlo Method [J].
Bouchard-Cote, Alexandre ;
Vollmer, Sebastian J. ;
Doucet, Arnaud .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2018, 113 (522) :855-867
[6]  
Brooks S, 2011, CH CRC HANDB MOD STA, pXIX
[7]   EXPONENTIAL ERGODICITY OF THE BOUNCY PARTICLE SAMPLER [J].
Deligiannidis, George ;
Bouchard-Cote, Alexandre ;
Doucet, Arnaud .
ANNALS OF STATISTICS, 2019, 47 (03) :1268-1287
[8]  
Ethier SN, 1986, MARKOV PROCESSES CHA
[9]   V-Subgeometric ergodicity for a Hastings-Metropolis algorithm [J].
Fort, G ;
Moulines, E .
STATISTICS & PROBABILITY LETTERS, 2000, 49 (04) :401-410
[10]   Subgeometric ergodicity of strong Markov processes [J].
Fort, G ;
Roberts, GO .
ANNALS OF APPLIED PROBABILITY, 2005, 15 (02) :1565-1589