Langevin diffusions and the Metropolis-adjusted Langevin algorithm

被引：70

作者：

Xifara, T. ^{[1
,2
]}

Sherlock, C. ^{[2
]}

Livingstone, S. ^{[3
]}

Byrne, S. ^{[3
]}

Girolami, M. ^{[3
]}

机构：

[1] Univ Calif Santa Cruz, Dept Appl Math & Stat, Santa Cruz, CA 95064 USA

[2] Univ Lancaster, Dept Math & Stat, Lancaster LA1 4YW, England

[3] UCL, Dept Stat Sci, London WC1E 6BT, England

来源：

STATISTICS & PROBABILITY LETTERS | 2014年 / 91卷

基金：

英国工程与自然科学研究理事会;

关键词：

Diffusions; Markov chain Monte Carlo; Metropolis-adjusted Langevin algorithm; Riemannian manifolds;

D O I：

10.1016/j.spl.2014.04.002

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 describe a Langevin diffusion with a target stationary density with respect to Lebesgue measure, as opposed to the volume measure of a previously-proposed diffusion. The two are sometimes equivalent but in general distinct and lead to different Metropolis-adjusted Langevin algorithms, which we compare. (C) 2014 Elsevier B.V. All rights reserved.

引用

页码：14 / 19

页数：6

共 11 条

[1]

[Anonymous], 1998, Stochastic differential equations

[2]

[Anonymous], 1995, Markov Chain Monte Carlo in Practice

[3]

Durrett R., 1996, STOCHASTIC CALCULAS

[4]

Federer Herbert, 1969, GEOMETRIC MEASURE TH

[5] Riemann manifold Langevin and Hamiltonian Monte Carlo methods [J].

Girolami, Mark ;

Calderhead, Ben .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2011, 73 :123-214

[6] TIME-REVERSIBLE DIFFUSIONS [J].

KENT, J .

ADVANCES IN APPLIED PROBABILITY, 1978, 10 (04) :819-835

[7]

Kloeden P.-E., 1992, STOCHASTIC MODELLING, V23

[8] Parameter estimation for differential equations: a generalized smoothing approach [J].

Ramsay, J. O. ;

Hooker, G. ;

Campbell, D. ;

Cao, J. .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2007, 69 :741-770

[9]

Roberts G., 2002, Methodology and Computing in Applied Probability, V4, P337, DOI [10.1023/A:1023562417138, DOI 10.1023/A:1023562417138]

[10]

Roberts G. O., 1996, Bernoulli, P341, DOI DOI 10.2307/3318418

← 1 2 →