Change search
ReferencesLink to record
Permanent link

Direct link
A large deviation analysis of certain qualitative properties of parallel tempering and infinite swapping algorithms
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematical Statistics.
2017 (English)In: Applied mathematics and optimization, ISSN 0095-4616, E-ISSN 1432-0606Article in journal (Refereed) Accepted
Abstract [en]

Parallel tempering, or replica exchange, is a popular method for simulating complex systems. The idea is to run parallel simulations at different temperatures, and at a given swap rate exchange configurations between the parallel simulations. From the perspective of large deviations it is optimal to let the swap rate tend to infinity and it is possible to construct a corresponding simulation scheme, known as infinite swapping. In this paper we propose a novel use of large deviations for empirical measures for a more detailed analysis of the infinite swapping limit in the setting of continuous time jump Markov processes. Using the large deviations rate function and associated stochastic control problems we consider a diagnostic based on temperature assignments, which can be easily computed during a simulation. We show that the convergence of this diagnostic to its a priori known limit is a necessary condition for the convergence of infinite swapping. The rate function is also used to investigate the impact of asymmetries in the underlying potential landscape, and where in the state space poor sampling is most likely to occur.

Place, publisher, year, edition, pages
2017.
Keyword [en]
Large deviatins, MCMC, parallel tempering, infinite swapping, ergodic control
National Category
Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:kth:diva-198612OAI: oai:DiVA.org:kth-198612DiVA: diva2:1057603
Note

QCR 20170111

Available from: 2016-12-19 Created: 2016-12-19 Last updated: 2017-01-11Bibliographically approved

Open Access in DiVA

No full text

Other links

arXiv

Search in DiVA

By author/editor
Nyquist, Pierre
By organisation
Mathematical Statistics
In the same journal
Applied mathematics and optimization
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar

Total: 1 hits
ReferencesLink to record
Permanent link

Direct link