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.

Tighter variational representations of f-divergences via restriction to probability measures

Simple item page
dc.contributor.authorRuderman, Avraham
dc.contributor.authorGarcia-Garcia, Dario
dc.contributor.authorPetterson, James
dc.contributor.authorReid, Mark
dc.coverage.spatialEdinburgh UK
dc.date.accessioned2015-12-10T23:33:10Z
dc.date.createdJune 26-July 1 2012
dc.date.issued2012
dc.date.updated2016-02-24T08:51:58Z
dc.description.abstractWe show that the variational representations for f-divergences currently used in the literature can be tightened. This has implications to a number of methods recently proposed based on this representation. As an example application we use our tighter representation to derive a general f-divergence estimator based on two i.i.d. samples and derive the dual program for this estimator that performs well empirically. We also point out a connection between our estimator and MMD.
dc.identifier.isbn9781450312851
dc.identifier.urihttp://hdl.handle.net/1885/69169
dc.publisherConference Organising Committee
dc.relation.ispartofseriesInternational Conference on Machine Learning (ICML 2012)
dc.sourceProceedings of the 29th International Conference on Machine Learning, ICML 2012
dc.subjectKeywords: Number of methods; Probability measures; Learning systems; Estimation
dc.titleTighter variational representations of f-divergences via restriction to probability measures
dc.typeConference paper
local.bibliographicCitation.lastpage678
local.bibliographicCitation.startpage671
local.contributor.affiliationRuderman, Avraham, College of Engineering and Computer Science, ANU
local.contributor.affiliationGarcia-Garcia, Dario, College of Engineering and Computer Science, ANU
local.contributor.affiliationPetterson, James, NICTA
local.contributor.affiliationReid, Mark, College of Engineering and Computer Science, ANU
local.contributor.authoruidRuderman, Avraham, u4971901
local.contributor.authoruidGarcia-Garcia, Dario, u5066131
local.contributor.authoruidReid, Mark, u4466898
local.description.embargo2037-12-31
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.ariespublicationf5625xPUB1941
local.identifier.scopusID2-s2.0-84867136405
local.type.statusPublished Version

Downloads

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
01_Ruderman_Tighter_variational_2012.pdf
Size:
502.67 KB
Format:
Adobe Portable Document Format
Download

Collections

ANU Research Publications

DSpace software copyright © 2002-2026 LYRASIS