Conditions for rapid mixing of parallel and simulated tempering on multimodal distributions

Published

Journal Article

We give conditions under which a Markov chain constructed via parallel or simulated tempering is guaranteed to be rapidly mixing, which are applicable to a wide range of multimodal distributions arising in Bayesian statistical inference and statistical mechanics. We provide lower bounds on the spectral gaps of parallel and simulated tempering. These bounds imply a single set of sufficient conditions for rapid mixing of both techniques. A direct consequence of our results is rapid mixing of parallel and simulated tempering for several normal mixture models, and for the mean-field Ising model. © Institute of Mathematical Statistics, 2009.

Full Text

Duke Authors

Cited Authors

  • Woodard, DB; Schmidler, SC; Huber, M

Published Date

  • April 1, 2009

Published In

Volume / Issue

  • 19 / 2

Start / End Page

  • 617 - 640

Electronic International Standard Serial Number (EISSN)

  • 1050-5164

International Standard Serial Number (ISSN)

  • 1050-5164

Digital Object Identifier (DOI)

  • 10.1214/08-AAP555

Citation Source

  • Scopus