Home > Research > Publications & Outputs > Hug and Hop

Electronic data

  • HugHop

    Rights statement: This is a pre-copy-editing, author-produced PDF of an article accepted for publication in British Journal for the Philosophy of Science following peer review. The definitive publisher-authenticated version M Ludkin, C Sherlock, Hug and Hop: a discrete-time, nonreversible Markov chain Monte Carlo algorithm, Biometrika, 2022;, asac039 is available online at: https://academic.oup.com/biomet/advance-article/doi/10.1093/biomet/asac039/6633932

    Accepted author manuscript, 2.22 MB, PDF document

    Embargo ends: 8/07/23

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

Text available via DOI:

View graph of relations

Hug and Hop: a discrete-time, nonreversible Markov chain Monte Carlo algorithm

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print
<mark>Journal publication date</mark>8/07/2022
<mark>Journal</mark>Biometrika
Number of pages15
Publication StatusE-pub ahead of print
Early online date8/07/22
<mark>Original language</mark>English

Abstract

We introduced the Hug and Hop Markov chain Monte Carlo algorithm for estimating expectations with respect to an intractable distribution. The algorithm alternates between two kernels: Hug and Hop. Hug is a non-reversible kernel that repeatedly applies the bounce mechanism from the recently proposed Bouncy Particle Sampler to produce a proposal point far from the current position, yet on almost the same contour of the target
density, leading to a high acceptance probability. Hug is complemented by Hop, which deliberately proposes jumps between contours and has an efficiency that degrades very slowly with increasing dimension. There are many parallels between Hug and Hamiltonian Monte Carlo using a leapfrog integrator, including the order of the integration scheme, however Hug is also able to make use of local Hessian information without requiring implicit numerical integration steps, and its performance is not terminally affected by unbounded gradients of the log-posterior. We test Hug and Hop empirically on a variety of toy targets and real statistical models and find that it can, and often does, outperform Hamiltonian Monte Carlo.

Bibliographic note

This is a pre-copy-editing, author-produced PDF of an article accepted for publication in British Journal for the Philosophy of Science following peer review. The definitive publisher-authenticated version M Ludkin, C Sherlock, Hug and Hop: a discrete-time, nonreversible Markov chain Monte Carlo algorithm, Biometrika, 2022;, asac039 is available online at: https://academic.oup.com/biomet/advance-article/doi/10.1093/biomet/asac039/6633932