2024-03-29T04:53:58Zhttp://uvadoc.uva.es/oai/requestoai:uvadoc.uva.es:10324/288502021-06-23T11:39:18Zcom_10324_1176com_10324_931com_10324_894col_10324_1359
Randomized Hamiltonian Monte Carlo
Bou-Rabee, Nawaf
Sanz Serna, Jesús María
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.
2018-03-01T10:52:08Z
2018-03-01T10:52:08Z
2017
info:eu-repo/semantics/article
The Annals of Applied Probability, 2017, Volume 27, Number 4, p. 2159-2194.
1050-5164
http://uvadoc.uva.es/handle/10324/28850
http://dx.doi.org/10.1214/16-AAP1255
eng
https://projecteuclid.org/euclid.aoap/1504080029
info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-nd/4.0/
Attribution-NonCommercial-NoDerivatives 4.0 International
SI