Information, Divergence and Risk for Binary Experiments

Simple item page
dc.contributor.authorReid, Mark
dc.contributor.authorWilliamson, Robert
dc.date.accessioned2015-12-07T22:14:35Z
dc.date.issued2011
dc.date.updated2019-05-19T08:25:00Z
dc.description.abstractWe unify f-divergences, Bregman divergences, surrogate regret bounds, proper scoring rules, cost curves, ROC-curves and statistical information. We do this by systematically studying integral and variational representations of these objects and in so doing identify their representation primitives which all are related to cost-sensitive binary classification. As well as developing relationships between generative and discriminative views of learning, the new machinery leads to tight and more general surrogate regret bounds and generalised Pinsker inequalities relating f-divergences to variational divergence. The new viewpoint also illuminates existing algorithms: it provides a new derivation of Support Vector Machines in terms of divergences and relates maximum mean discrepancy to Fisher linear discriminants.
dc.identifier.issn1532-4435
dc.identifier.urihttp://hdl.handle.net/1885/17495
dc.publisherMIT Press
dc.rightsAuthor/s retain copyright
dc.sourceJournal of Machine Learning Research
dc.source.urihttp://jmlr.csail.mit.edu/papers/v12/reid11a.html
dc.subjectKeywords: Classification; Divergence; Loss functions; Regret bounds; Statistical information; Machinery; Statistics Classification; Divergence; Loss functions; Regret bounds; Statistical information
dc.titleInformation, Divergence and Risk for Binary Experiments
dc.typeJournal article
dcterms.accessRightsOpen Accessen_AU
local.bibliographicCitation.issueMarch
local.bibliographicCitation.lastpage817
local.bibliographicCitation.startpage731
local.contributor.affiliationReid, Mark, College of Engineering and Computer Science, ANU
local.contributor.affiliationWilliamson, Robert, College of Engineering and Computer Science, ANU
local.contributor.authoremailu4466898@anu.edu.au
local.contributor.authoruidReid, Mark, u4466898
local.contributor.authoruidWilliamson, Robert, u9000163
local.description.notesImported from ARIES
local.identifier.absfor080109 - Pattern Recognition and Data Mining
local.identifier.absseo970108 - Expanding Knowledge in the Information and Computing Sciences
local.identifier.ariespublicationu9000163xPUB1
local.identifier.citationvolume12
local.identifier.scopusID2-s2.0-79955815221
local.identifier.thomsonID000289635000003
local.identifier.uidSubmittedByu9000163
local.type.statusPublished Version

Downloads

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
01_Reid_Information,_Divergence_and_2011.pdf
Size:
1.44 MB
Format:
Adobe Portable Document Format
Download

Collections

ANU Research Publications

DSpace software copyright © 2002-2024 LYRASIS