License: Creative Commons Attribution 3.0 Unported license (CC BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.APPROX-RANDOM.2019.64
URN: urn:nbn:de:0030-drops-112790
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2019/11279/
Go to the corresponding LIPIcs Volume Portal

Chen, Zongchen ; Vempala, Santosh S.

Optimal Convergence Rate of Hamiltonian Monte Carlo for Strongly Logconcave Distributions

pdf-format:
LIPIcs-APPROX-RANDOM-2019-64.pdf (0.4 MB)

Abstract

We study Hamiltonian Monte Carlo (HMC) for sampling from a strongly logconcave density proportional to e^{-f} where f:R^d -> R is mu-strongly convex and L-smooth (the condition number is kappa = L/mu). We show that the relaxation time (inverse of the spectral gap) of ideal HMC is O(kappa), improving on the previous best bound of O(kappa^{1.5}); we complement this with an example where the relaxation time is Omega(kappa). When implemented using a nearly optimal ODE solver, HMC returns an epsilon-approximate point in 2-Wasserstein distance using O~((kappa d)^{0.5} epsilon^{-1}) gradient evaluations per step and O~((kappa d)^{1.5}epsilon^{-1}) total time.

BibTeX - Entry

@InProceedings{chen_et_al:LIPIcs:2019:11279,
  author =	{Zongchen Chen and Santosh S. Vempala},
  title =	{{Optimal Convergence Rate of Hamiltonian Monte Carlo for Strongly Logconcave Distributions}},
  booktitle =	{Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2019)},
  pages =	{64:1--64:12},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-125-2},
  ISSN =	{1868-8969},
  year =	{2019},
  volume =	{145},
  editor =	{Dimitris Achlioptas and L{\'a}szl{\'o} A. V{\'e}gh},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2019/11279},
  URN =		{urn:nbn:de:0030-drops-112790},
  doi =		{10.4230/LIPIcs.APPROX-RANDOM.2019.64},
  annote =	{Keywords: logconcave distribution, sampling, Hamiltonian Monte Carlo, spectral gap, strong convexity}
}

Keywords: logconcave distribution, sampling, Hamiltonian Monte Carlo, spectral gap, strong convexity
Collection: Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2019)
Issue Date: 2019
Date of publication: 17.09.2019

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI