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.

Convexity of proper composite binary losses

dc.contributor.authorReid, Mark D.en
dc.contributor.authorWilliamson, Robert C.en
dc.date.accessioned2026-01-01T07:42:08Z
dc.date.available2026-01-01T07:42:08Z
dc.date.issued2010en
dc.description.abstractA composite loss assigns a penalty to a real-valued prediction by associating the prediction with a probability via a link function then applying a class probability estimation (CPE) loss. If the risk for a composite loss is always minimised by predicting the value associated with the true class probability the composite loss is proper. We provide a novel, explicit and complete characterisation of the convexity of any proper composite loss in terms of its link and its \weight function" associated with its proper CPE loss.en
dc.description.statusPeer-revieweden
dc.format.extent8en
dc.identifier.issn1532-4435en
dc.identifier.scopus84862287353en
dc.identifier.urihttps://hdl.handle.net/1885/733798930
dc.language.isoenen
dc.relation.ispartofseries13th International Conference on Artificial Intelligence and Statistics, AISTATS 2010en
dc.sourceJournal of Machine Learning Researchen
dc.titleConvexity of proper composite binary lossesen
dc.typeConference paperen
dspace.entity.typePublicationen
local.bibliographicCitation.lastpage644en
local.bibliographicCitation.startpage637en
local.contributor.affiliationReid, Mark D.; School of Computing, ANU College of Systems and Society, The Australian National Universityen
local.contributor.affiliationWilliamson, Robert C.; School of Computing, ANU College of Systems and Society, The Australian National Universityen
local.identifier.ariespublicationu3485190xPUB19en
local.identifier.citationvolume9en
local.identifier.pure06336ae8-05be-4b74-93c3-f6b7fc1d66feen
local.identifier.urlhttps://www.scopus.com/pages/publications/84862287353en
local.type.statusPublisheden

Downloads