CUED Publications database

The geometric foundations of Hamiltonian Monte Carlo

Betancourt, M and Byrne, S and Livingstone, S and Girolami, M (2017) The geometric foundations of Hamiltonian Monte Carlo. Bernoulli: a journal of mathematical statistics and probability, 23. pp. 2257-2298. ISSN 1350-7265

Full text not available from this repository.

Abstract

© 2017 ISI/BS. Although Hamiltonian Monte Carlo has proven an empirical success, the lack of a rigorous theoretical understanding of the algorithm has in many ways impeded both principled developments of the method and use of the algorithm in practice. In this paper, we develop the formal foundations of the algorithm through the construction of measures on smooth manifolds, and demonstrate how the theory naturally identifies efficient implementations and motivates promising generalizations.

Item Type: Article
Subjects: UNSPECIFIED
Divisions: UNSPECIFIED
Depositing User: Cron Job
Date Deposited: 23 Mar 2020 20:02
Last Modified: 10 Apr 2021 01:20
DOI: 10.3150/16-BEJ810