The Geometric Foundations of Hamiltonian Monte Carlo
Methodology
2014-10-21 v1
Abstract
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.
Keywords
Cite
@article{arxiv.1410.5110,
title = {The Geometric Foundations of Hamiltonian Monte Carlo},
author = {M. J. Betancourt and Simon Byrne and Samuel Livingstone and Mark Girolami},
journal= {arXiv preprint arXiv:1410.5110},
year = {2014}
}
Comments
45 pages, 13 figures