Show simple item record

dc.contributor.authorSontag, David
dc.contributor.authorMeshi, Ofer
dc.contributor.authorJaakkola, Tommi S.
dc.contributor.authorGloberson, Amir
dc.date.accessioned2011-07-06T14:56:22Z
dc.date.available2011-07-06T14:56:22Z
dc.date.issued2010-12
dc.identifier.urihttp://hdl.handle.net/1721.1/64743
dc.description.abstractThe problem of learning to predict structured labels is of key importance in many applications. However, for general graph structure both learning and inference in this setting are intractable. Here we show that it is possible to circumvent this difficulty when the input distribution is rich enough via a method similar in spirit to pseudo-likelihood. We show how our new method achieves consistency, and illustrate empirically that it indeed performs as well as exact methods when sufficiently large training sets are used.en_US
dc.description.sponsorshipUnited States-Israel Binational Science Foundation (Grant 2008303)en_US
dc.description.sponsorshipGoogle (Firm) (Research Grant)en_US
dc.description.sponsorshipGoogle (Firm) (PhD Fellowship)en_US
dc.language.isoen_US
dc.publisherNeural Information Processing Systems Foundationen_US
dc.relation.isversionofhttp://books.nips.cc/papers/files/nips23/NIPS2010_0809.pdfen_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.sourceMIT web domainen_US
dc.titleMore data means less inference: A pseudo-max approach to structured learningen_US
dc.typeArticleen_US
dc.identifier.citationSontag, David et al. "More data means less inference: A pseudo-max approach to structured learning." in Proceedins of the Twenty-Fourth Annual Conference on Neural Information Processing Systems, NIPS 2010, Poster Session, December 6-9, Vancouver, B.C., Canada.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.approverJaakkola, Tommi S.
dc.contributor.mitauthorJaakkola, Tommi S.
dc.relation.journalPoster Session paper of the Twenty-Fourth Annual Conference on Neural Information Processing Systems, NIPS 2010en_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
dspace.orderedauthorsSontag, David; Meshi, Ofer; Jaakkola, Tommi; Globerson, Amir
dc.identifier.orcidhttps://orcid.org/0000-0002-2199-0379
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