Show simple item record

dc.contributor.authorBresler, Guy
dc.contributor.authorGamarnik, David
dc.contributor.authorShah, Devavrat
dc.date.accessioned2015-09-18T16:39:39Z
dc.date.available2015-09-18T16:39:39Z
dc.date.issued2014-09
dc.identifier.isbn978-1-4799-8009-3
dc.identifier.urihttp://hdl.handle.net/1721.1/98837
dc.description.abstractIn this paper we consider the problem of learning undirected graphical models from data generated according to the Glauber dynamics. The Glauber dynamics is a Markov chain that sequentially updates individual nodes (variables) in a graphical model and it is frequently used to sample from the stationary distribution (to which it converges given sufficient time). Additionally, the Glauber dynamics is a natural dynamical model in a variety of settings. This work deviates from the standard formulation of graphical model learning in the literature, where one assumes access to i.i.d. samples from the distribution. Much of the research on graphical model learning has been directed towards finding algorithms with low computational cost. As the main result of this work, we establish that the problem of reconstructing binary pairwise graphical models is computationally tractable when we observe the Glauber dynamics. Specifically, we show that a binary pairwise graphical model on p nodes with maximum degree d can be learned in time f(d)p[superscript 3] log p, for a function f(d), using nearly the information-theoretic minimum possible number of samples. There is no known algorithm of comparable efficiency for learning arbitrary binary pairwise models from i.i.d. samples.en_US
dc.description.sponsorshipNational Science Foundation (U.S.) (Grant CMMI-1335155)en_US
dc.description.sponsorshipNational Science Foundation (U.S.) (Grant CNS-1161964)en_US
dc.description.sponsorshipUnited States. Army Research Office. Multidisciplinary University Research Initiative (Award W911NF-11-1-0036)en_US
dc.language.isoen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/ALLERTON.2014.7028584en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcearXiven_US
dc.titleLearning graphical models from the Glauber dynamicsen_US
dc.typeArticleen_US
dc.identifier.citationBresler, Guy, David Gamarnik, and Devavrat Shah. “Learning Graphical Models from the Glauber Dynamics.” 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton) (September 2014).en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.departmentSloan School of Managementen_US
dc.contributor.mitauthorBresler, Guyen_US
dc.contributor.mitauthorGamarnik, Daviden_US
dc.contributor.mitauthorShah, Devavraten_US
dc.relation.journalProceedings of the 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton)en_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dspace.orderedauthorsBresler, Guy; Gamarnik, David; Shah, Devavraten_US
dc.identifier.orcidhttps://orcid.org/0000-0001-8898-8778
dc.identifier.orcidhttps://orcid.org/0000-0003-0737-3259
dc.identifier.orcidhttps://orcid.org/0000-0003-1303-582X
mit.licenseOPEN_ACCESS_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record