Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

Composite Multiclass Losses

Simple item page
dc.contributor.authorVernet, Elodie
dc.contributor.authorWilliamson, Robert
dc.contributor.authorReid, Mark
dc.contributor.editorRich Zemel
dc.contributor.editorJohn Shawe-Taylor
dc.contributor.editorPeter Bartlett
dc.contributor.editorFernando Pereira
dc.contributor.editorKilian Weinb
dc.coverage.spatialGranada Spain
dc.date.accessioned2015-12-10T21:56:50Z
dc.date.createdDecember 13-15 2011
dc.date.issued2011
dc.date.updated2019-05-19T08:23:15Z
dc.description.abstractWe consider loss functions for multiclass prediction problems. We show when a multiclass loss can be expressed as a "proper composite loss", which is the composition of a proper loss and a link function. We extend existing results for binary losses to mul
dc.identifier.isbn9781618395993
dc.identifier.urihttp://hdl.handle.net/1885/39622
dc.publisherNeural Information Processing Systems Foundation
dc.relation.ispartofseriesNeural Information Processing Systems (NIPS 2011)
dc.rightsAuthor/s retain copyright
dc.sourceAdvances in Neural Information Processing Systems 23
dc.source.urihttp://papers.nips.cc/book/advances-in-neural-information-processing-systems-24-2011
dc.subjectKeywords: Existence and uniqueness; Integral representation; Loss functions; Multi-class; Multiclass prediction; Properness; Stationarity
dc.titleComposite Multiclass Losses
dc.typeConference paper
dcterms.accessRightsOpen Accessen_AU
local.bibliographicCitation.startpage15
local.contributor.affiliationVernet, Elodie, College of Engineering and Computer Science, ANU
local.contributor.affiliationWilliamson, Robert, College of Engineering and Computer Science, ANU
local.contributor.affiliationReid, Mark, College of Engineering and Computer Science, ANU
local.contributor.authoruidVernet, Elodie, t1459
local.contributor.authoruidWilliamson, Robert, u9000163
local.contributor.authoruidReid, Mark, u4466898
local.description.notesImported from ARIES
local.description.refereedYes
local.identifier.absfor080109 - Pattern Recognition and Data Mining
local.identifier.absseo970108 - Expanding Knowledge in the Information and Computing Sciences
local.identifier.ariespublicationu4963866xPUB180
local.identifier.scopusID2-s2.0-84889719934
local.type.statusPublished Version

Downloads

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
01_Vernet_Composite_Multiclass_Los_2011.pdf
Size:
469.95 KB
Format:
Adobe Portable Document Format
Download

Collections

ANU Research Publications

DSpace software copyright © 2002-2026 LYRASIS