Skip navigation
Skip navigation

Risk-based generalizations of f-divergences

Garcia-Garcia, Dario; von Luxburg, Ulrike; Santos-Rodriguez, Raul

Description

We derive a generalized notion of f-divergences, called (f,l)-divergences. We show that this generalization enjoys many of the nice properties of/-divergences, although it is a richer family. It also provides alternative definitions of standard divergences in terms of surrogate risks. As a first practical application of this theory, we derive a new estimator for the Kulback-Leibler divergence that we use for clustering sets of vectors.

dc.contributor.authorGarcia-Garcia, Dario
dc.contributor.authorvon Luxburg, Ulrike
dc.contributor.authorSantos-Rodriguez, Raul
dc.coverage.spatialWashington USA
dc.date.accessioned2015-12-07T22:14:24Z
dc.date.createdJune 28-July 2 2011
dc.identifier.urihttp://hdl.handle.net/1885/17402
dc.description.abstractWe derive a generalized notion of f-divergences, called (f,l)-divergences. We show that this generalization enjoys many of the nice properties of/-divergences, although it is a richer family. It also provides alternative definitions of standard divergences in terms of surrogate risks. As a first practical application of this theory, we derive a new estimator for the Kulback-Leibler divergence that we use for clustering sets of vectors.
dc.publisherOmniPress
dc.relation.ispartofseriesInternational Conference on Machine Learning (ICML 2011)
dc.sourceMax-margin Learning for Lower Linear Envelope Potentials in Binary Markov Random Fields
dc.subjectKeywords: Risk-based; Learning systems
dc.titleRisk-based generalizations of f-divergences
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2011
local.identifier.absfor170203 - Knowledge Representation and Machine Learning
local.identifier.ariespublicationu5066131xPUB1
local.type.statusPublished Version
local.contributor.affiliationGarcia-Garcia, Dario, College of Engineering and Computer Science, ANU
local.contributor.affiliationvon Luxburg, Ulrike, Max Planck Institute for Biological Cybernetics
local.contributor.affiliationSantos-Rodriguez, Raul, Universidad Carlos III de Madrid
local.description.embargo2037-12-31
dc.date.updated2016-02-24T11:33:59Z
local.identifier.scopusID2-s2.0-80053460732
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Garcia-Garcia_Risk-based_generalizations_of_2011.pdf170.56 kBAdobe PDFThumbnail
02_Garcia-Garcia_Risk-based_generalizations_of_2011.pdf272.11 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator