MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Open Access Articles
  • MIT Open Access Articles
  • View Item
  • DSpace@MIT Home
  • MIT Open Access Articles
  • MIT Open Access Articles
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

A large-deviation analysis for the maximum likelihood learning of tree structures

Author(s)
Tong, Lang; Tan, Vincent Yan Fu; Anandkumar, Animashree; Willsky, Alan S.
Thumbnail
DownloadAnandkumar-2009-A large-deviation analysis for the maximum likelihood learning of tree structures.pdf (992.0Kb)
PUBLISHER_POLICY

Publisher Policy

Article 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.

Terms of use
Article 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.
Metadata
Show full item record
Abstract
The 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.
Date issued
2009-08
URI
http://hdl.handle.net/1721.1/58826
Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Stochastic Systems Group
Journal
IEEE International Symposium on Information Theory, 2009. ISIT 2009.
Citation
Tan, 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.
Version: Final published version
Other identifiers
INSPEC Accession Number: 10842161
ISBN
978-1-4244-4312-3
Keywords
Error exponents, Euclidean Information Theory, Large-deviations, Tree structure learning

Collections
  • MIT Open Access Articles

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.