Home > Research > Publications & Outputs > An adaptive sequential Monte Carlo sampler

Electronic data

  • Fearnhead

    Rights statement: © 2013 International Society for Bayesian Analysis

    Final published version, 289 KB, PDF document

Links

Text available via DOI:

View graph of relations

An adaptive sequential Monte Carlo sampler

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

An adaptive sequential Monte Carlo sampler. / Fearnhead, Paul; Taylor, Benjamin M.
In: Bayesian Analysis, Vol. 8, No. 2, 2013, p. 411-438.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Fearnhead, P & Taylor, BM 2013, 'An adaptive sequential Monte Carlo sampler', Bayesian Analysis, vol. 8, no. 2, pp. 411-438. https://doi.org/10.1214/13-BA814

APA

Fearnhead, P., & Taylor, B. M. (2013). An adaptive sequential Monte Carlo sampler. Bayesian Analysis, 8(2), 411-438. https://doi.org/10.1214/13-BA814

Vancouver

Fearnhead P, Taylor BM. An adaptive sequential Monte Carlo sampler. Bayesian Analysis. 2013;8(2):411-438. Epub 2013 Mar 6. doi: 10.1214/13-BA814

Author

Fearnhead, Paul ; Taylor, Benjamin M. / An adaptive sequential Monte Carlo sampler. In: Bayesian Analysis. 2013 ; Vol. 8, No. 2. pp. 411-438.

Bibtex

@article{9e15de9ad86548828c46a63d260504e0,
title = "An adaptive sequential Monte Carlo sampler",
abstract = "Sequential Monte Carlo (SMC) methods are not only a popular toolin the analysis of state–space models, but offer an alternative to Markov chainMonte Carlo (MCMC) in situations where Bayesian inference must proceed viasimulation. This paper introduces a new SMC method that uses adaptive MCMC kernels for particle dynamics. The proposed algorithm features an online stochastic optimization procedure to select the best MCMC kernel and simultaneously learn optimal tuning parameters. Theoretical results are presented that justify the approach and give guidance on how it should be implemented. Empirical results, based on analysing data from mixture models, show that the new adaptive SMC algorithm (ASMC) can both choose the best MCMC kernel, and learn an appropriate scaling for it. ASMC with a choice between kernels outperformed the adaptive MCMC algorithm of Haario et al. (1998) in 5 out of the 6 cases considered.",
keywords = "Adaptive MCMC, Adaptive Sequential Monte Carlo, Bayesian Mixture Analysis, Optimal Scaling, Stochastic Optimization",
author = "Paul Fearnhead and Taylor, {Benjamin M.}",
note = "{\textcopyright} 2013 International Society for Bayesian Analysis",
year = "2013",
doi = "10.1214/13-BA814",
language = "English",
volume = "8",
pages = "411--438",
journal = "Bayesian Analysis",
issn = "1931-6690",
publisher = "Carnegie Mellon University",
number = "2",

}

RIS

TY - JOUR

T1 - An adaptive sequential Monte Carlo sampler

AU - Fearnhead, Paul

AU - Taylor, Benjamin M.

N1 - © 2013 International Society for Bayesian Analysis

PY - 2013

Y1 - 2013

N2 - Sequential Monte Carlo (SMC) methods are not only a popular toolin the analysis of state–space models, but offer an alternative to Markov chainMonte Carlo (MCMC) in situations where Bayesian inference must proceed viasimulation. This paper introduces a new SMC method that uses adaptive MCMC kernels for particle dynamics. The proposed algorithm features an online stochastic optimization procedure to select the best MCMC kernel and simultaneously learn optimal tuning parameters. Theoretical results are presented that justify the approach and give guidance on how it should be implemented. Empirical results, based on analysing data from mixture models, show that the new adaptive SMC algorithm (ASMC) can both choose the best MCMC kernel, and learn an appropriate scaling for it. ASMC with a choice between kernels outperformed the adaptive MCMC algorithm of Haario et al. (1998) in 5 out of the 6 cases considered.

AB - Sequential Monte Carlo (SMC) methods are not only a popular toolin the analysis of state–space models, but offer an alternative to Markov chainMonte Carlo (MCMC) in situations where Bayesian inference must proceed viasimulation. This paper introduces a new SMC method that uses adaptive MCMC kernels for particle dynamics. The proposed algorithm features an online stochastic optimization procedure to select the best MCMC kernel and simultaneously learn optimal tuning parameters. Theoretical results are presented that justify the approach and give guidance on how it should be implemented. Empirical results, based on analysing data from mixture models, show that the new adaptive SMC algorithm (ASMC) can both choose the best MCMC kernel, and learn an appropriate scaling for it. ASMC with a choice between kernels outperformed the adaptive MCMC algorithm of Haario et al. (1998) in 5 out of the 6 cases considered.

KW - Adaptive MCMC

KW - Adaptive Sequential Monte Carlo

KW - Bayesian Mixture Analysis

KW - Optimal Scaling

KW - Stochastic Optimization

U2 - 10.1214/13-BA814

DO - 10.1214/13-BA814

M3 - Journal article

VL - 8

SP - 411

EP - 438

JO - Bayesian Analysis

JF - Bayesian Analysis

SN - 1931-6690

IS - 2

ER -