Show simple item record

dc.contributor.authorWillsky, Alan S.
dc.contributor.authorTan, Vincent Yan Fu
dc.contributor.authorAnandkumar, Animashree
dc.date.accessioned2012-10-04T13:43:41Z
dc.date.available2012-10-04T13:43:41Z
dc.date.issued2010-09
dc.date.submitted2010-09
dc.identifier.isbn978-1-4244-8215-3
dc.identifier.urihttp://hdl.handle.net/1721.1/73590
dc.description.abstractThe problem of learning forest-structured discrete graphical models from i.i.d. samples is considered. An algorithm based on pruning of the Chow-Liu tree through adaptive thresholding is proposed. It is shown that this algorithm is structurally consistent and the error probability of structure learning decays faster than any polynomial in the number of samples under fixed model size. For the high-dimensional scenario where the size of the model d and the number of edges k scale with the number of samples n, sufficient conditions on (n, d, k) are given for the algorithm to be structurally consistent. In addition, the extremal structures for learning are identified; we prove that the independent (resp. tree) model is the hardest (resp. easiest) to learn using the proposed algorithm in terms of error rates for structure learning.en_US
dc.description.sponsorshipUnited States. Air Force Office of Scientific Research (Grant FA9559-08-1- 1080)en_US
dc.description.sponsorshipUnited States. Army Research Office. Multidisciplinary University Research Initiative (Grant W911NF-06-1-0076)en_US
dc.description.sponsorshipUnited States. Army Research Office. Multidisciplinary University Research Initiative (Grant FA9550-06-1-0324)en_US
dc.description.sponsorshipSingapore. Agency for Science, Technology and Researchen_US
dc.language.isoen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/ALLERTON.2010.5706977en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alike 3.0en_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/en_US
dc.sourceOther University Web Domainen_US
dc.titleScaling laws for learning high-dimensional Markov forest distributionsen_US
dc.typeArticleen_US
dc.identifier.citationTan, Vincent Y. F., Animashree Anandkumar, and Alan S. Wi. "Scaling laws for learning high-dimensional Markov forest distributions" 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton), 2010. 712–718.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.departmentMassachusetts Institute of Technology. Laboratory for Information and Decision Systemsen_US
dc.contributor.mitauthorWillsky, Alan S.
dc.contributor.mitauthorTan, Vincent Yan Fu
dc.contributor.mitauthorAnandkumar, Animashree
dc.relation.journalProceedings of the 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton), 2010en_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
dspace.orderedauthorsTan, Vincent Y. F.; Anandkumar, Animashree; Willsky, Alan S.en
dc.identifier.orcidhttps://orcid.org/0000-0003-0149-5888
mit.licenseOPEN_ACCESS_POLICYen_US
mit.metadata.statusComplete


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record