Show simple item record

dc.contributor.authorTong, Lang
dc.contributor.authorTan, Vincent Yan Fu
dc.contributor.authorAnandkumar, Animashree
dc.contributor.authorWillsky, Alan S.
dc.date.accessioned2010-10-01T17:02:13Z
dc.date.available2010-10-01T17:02:13Z
dc.date.issued2009-08
dc.identifier.isbn978-1-4244-4312-3
dc.identifier.otherINSPEC Accession Number: 10842161
dc.identifier.urihttp://hdl.handle.net/1721.1/58826
dc.description.abstractThe problem of maximum-likelihood learning of the structure of an unknown discrete distribution from samples is considered when the distribution is Markov on a tree. Large-deviation analysis of the error in estimation of the set of edges of the tree is performed. Necessary and sufficient conditions are provided to ensure that this error probability decays exponentially. These conditions are based on the mutual information between each pair of variables being distinct from that of other pairs. The rate of error decay, or error exponent, is derived using the large-deviation principle. The error exponent is approximated using Euclidean information theory and is given by a ratio, to be interpreted as the signal-to-noise ratio (SNR) for learning. Numerical experiments show the SNR approximation is accurate.en_US
dc.language.isoen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/ISIT.2009.5206012en_US
dc.rightsArticle is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.en_US
dc.sourceIEEEen_US
dc.subjectError exponentsen_US
dc.subjectEuclidean Information Theoryen_US
dc.subjectLarge-deviationsen_US
dc.subjectTree structure learningen_US
dc.titleA large-deviation analysis for the maximum likelihood learning of tree structuresen_US
dc.typeArticleen_US
dc.identifier.citationTan, V.Y.F. et al. “A large-deviation analysis for the maximum likelihood learning of tree structures.” Information Theory, 2009. ISIT 2009. IEEE International Symposium on. 2009. 1140-1144. Web.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.departmentMassachusetts Institute of Technology. Stochastic Systems Groupen_US
dc.contributor.approverWillsky, Alan S.
dc.contributor.mitauthorTan, Vincent Yan Fu
dc.contributor.mitauthorAnandkumar, Animashree
dc.contributor.mitauthorWillsky, Alan S.
dc.relation.journalIEEE International Symposium on Information Theory, 2009. ISIT 2009.en_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dspace.orderedauthorsTan, Vincent Y. F.; Anandkumar, Animashree; Tong, Lang; Willsky, Alan S.en
dc.identifier.orcidhttps://orcid.org/0000-0003-0149-5888
mit.licensePUBLISHER_POLICYen_US
mit.metadata.statusComplete


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record