Home > Research > Publications & Outputs > The Apogee to Apogee Path Sampler

Research

Associated organisational unit

Electronic data

  • The Apogee to Apogee Path Sampler

    Rights statement: 12m

    Accepted author manuscript, 1.07 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

Keywords

View graph of relations

The Apogee to Apogee Path Sampler

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

The Apogee to Apogee Path Sampler. / Sherlock, Chris; Urbas, Szymon; Ludkin, Matthew.
In: Journal of Computational and Graphical Statistics, Vol. 32, No. 4, 02.10.2023, p. 1436-1446.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Sherlock, C, Urbas, S & Ludkin, M 2023, 'The Apogee to Apogee Path Sampler', Journal of Computational and Graphical Statistics, vol. 32, no. 4, pp. 1436-1446. https://doi.org/10.1080/10618600.2023.2190784

APA

Sherlock, C., Urbas, S., & Ludkin, M. (2023). The Apogee to Apogee Path Sampler. Journal of Computational and Graphical Statistics, 32(4), 1436-1446. https://doi.org/10.1080/10618600.2023.2190784

Vancouver

Sherlock C, Urbas S, Ludkin M. The Apogee to Apogee Path Sampler. Journal of Computational and Graphical Statistics. 2023 Oct 2;32(4):1436-1446. Epub 2023 Apr 24. doi: 10.1080/10618600.2023.2190784

Author

Sherlock, Chris ; Urbas, Szymon ; Ludkin, Matthew. / The Apogee to Apogee Path Sampler. In: Journal of Computational and Graphical Statistics. 2023 ; Vol. 32, No. 4. pp. 1436-1446.

Bibtex

@article{aa50bcf3c9dc4c62a6e467f58c540cda,
title = "The Apogee to Apogee Path Sampler",
abstract = "Among Markov chain Monte Carlo algorithms, Hamiltonian Monte Carlo (HMC) is often the algorithm of choice for complex, high-dimensional target distributions; however, its efficiency is notoriously sensitive to the choice of the integration-time tuning parameter. When integrating both forward and backward in time using the same leapfrog integration step as HMC, the set of apogees, local maxima in the potential along a path, is the same whatever point (position and momentum) along the path is chosen to initialize the integration. We present the Apogee to Apogee Path Sampler (AAPS), which uses this invariance to create a simple yet generic methodology for constructing a path, proposing a point from it and accepting or rejecting that proposal so as to target the intended distribution. We demonstrate empirically that AAPS has a similar efficiency to HMC but is much more robust to the setting of its equivalent tuning parameter, the number of apogees that the path crosses. Supplementary materials for this article are available online.",
keywords = "Hamiltonian Monte Carlo, Leapfrog step, Markov chain Monte Carlo, Robustness to tuning",
author = "Chris Sherlock and Szymon Urbas and Matthew Ludkin",
year = "2023",
month = oct,
day = "2",
doi = "10.1080/10618600.2023.2190784",
language = "English",
volume = "32",
pages = "1436--1446",
journal = "Journal of Computational and Graphical Statistics",
issn = "1061-8600",
publisher = "American Statistical Association",
number = "4",

}

RIS

TY - JOUR

T1 - The Apogee to Apogee Path Sampler

AU - Sherlock, Chris

AU - Urbas, Szymon

AU - Ludkin, Matthew

PY - 2023/10/2

Y1 - 2023/10/2

N2 - Among Markov chain Monte Carlo algorithms, Hamiltonian Monte Carlo (HMC) is often the algorithm of choice for complex, high-dimensional target distributions; however, its efficiency is notoriously sensitive to the choice of the integration-time tuning parameter. When integrating both forward and backward in time using the same leapfrog integration step as HMC, the set of apogees, local maxima in the potential along a path, is the same whatever point (position and momentum) along the path is chosen to initialize the integration. We present the Apogee to Apogee Path Sampler (AAPS), which uses this invariance to create a simple yet generic methodology for constructing a path, proposing a point from it and accepting or rejecting that proposal so as to target the intended distribution. We demonstrate empirically that AAPS has a similar efficiency to HMC but is much more robust to the setting of its equivalent tuning parameter, the number of apogees that the path crosses. Supplementary materials for this article are available online.

AB - Among Markov chain Monte Carlo algorithms, Hamiltonian Monte Carlo (HMC) is often the algorithm of choice for complex, high-dimensional target distributions; however, its efficiency is notoriously sensitive to the choice of the integration-time tuning parameter. When integrating both forward and backward in time using the same leapfrog integration step as HMC, the set of apogees, local maxima in the potential along a path, is the same whatever point (position and momentum) along the path is chosen to initialize the integration. We present the Apogee to Apogee Path Sampler (AAPS), which uses this invariance to create a simple yet generic methodology for constructing a path, proposing a point from it and accepting or rejecting that proposal so as to target the intended distribution. We demonstrate empirically that AAPS has a similar efficiency to HMC but is much more robust to the setting of its equivalent tuning parameter, the number of apogees that the path crosses. Supplementary materials for this article are available online.

KW - Hamiltonian Monte Carlo

KW - Leapfrog step

KW - Markov chain Monte Carlo

KW - Robustness to tuning

U2 - 10.1080/10618600.2023.2190784

DO - 10.1080/10618600.2023.2190784

M3 - Journal article

VL - 32

SP - 1436

EP - 1446

JO - Journal of Computational and Graphical Statistics

JF - Journal of Computational and Graphical Statistics

SN - 1061-8600

IS - 4

ER -