Skip navigation
Please use this identifier to cite or link to this item:
Title: Randomized Hamiltonian Monte Carlo
Authors: Bou-Rabee, Nawaf
Sanz Serna, Jesús María
Issue Date: 2017
Citation: The Annals of Applied Probability, 2017, Volume 27, Number 4, p. 2159-2194.
Abstract: Tuning the durations of the Hamiltonian flow in Hamiltonian Monte Carlo (also called Hybrid Monte Carlo) (HMC) involves a tradeoff between computational cost and sampling quality, which is typically challenging to resolve in a satisfactory way. In this article, we present and analyze a randomized HMC method (RHMC), in which these durations are i.i.d. exponential random variables whose mean is a free parameter. We focus on the small time step size limit, where the algorithm is rejection-free and the computational cost is proportional to the mean duration. In this limit, we prove that RHMC is geometrically ergodic under the same conditions that imply geometric ergodicity of the solution to underdamped Langevin equations. Moreover, in the context of a multidimensional Gaussian distribution, we prove that the sampling efficiency of RHMC, unlike that of constant duration HMC, behaves in a regular way. This regularity is also verified numerically in non-Gaussian target distributions. Finally, we suggest variants of RHMC for which the time step size is not required to be small.
ISSN: 1050-5164
Peer Review: SI
Sponsor: Ministerio de Economía, Industria y Competitividad (Project MTM2013-46553-C3-1-P).
Publisher Version:
Language: eng
Rights: info:eu-repo/semantics/openAccess
Appears in Collections:DEP51 - Artículos de revista

Files in This Item:
File Description SizeFormat 
euclid.aoap.1504080029.pdf819,94 kBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons

University of Valladolid
Powered by MIT's. DSpace software, Version 5.5