Skip navigation
Skip navigation

Convex learning with invariances

Teo, Choon-Hui; Globerson, Amir; Roweis, Sam; Smola, Alexander

Description

Incorporating invariances into a learning algorithm is a common problem in machine learning. We provide a convex formulation which can deal with arbitrary loss functions and arbitrary losses. In addition, it is a drop-in replacement for most optimization

dc.contributor.authorTeo, Choon-Hui
dc.contributor.authorGloberson, Amir
dc.contributor.authorRoweis, Sam
dc.contributor.authorSmola, Alexander
dc.coverage.spatialVancouver Canada
dc.date.accessioned2015-12-10T22:25:40Z
dc.date.createdDecember 3-8 2007
dc.identifier.urihttp://hdl.handle.net/1885/53583
dc.description.abstractIncorporating invariances into a learning algorithm is a common problem in machine learning. We provide a convex formulation which can deal with arbitrary loss functions and arbitrary losses. In addition, it is a drop-in replacement for most optimization
dc.publisherMIT Press
dc.relation.ispartofseriesConference on Advances in Neural Information Processing Systems (NIPS 2007)
dc.sourceAdvances in Neural Information Processing Systems 20: Proceedings of the 2007 Conference
dc.source.urihttp://books.nips.cc/nips20.html
dc.subjectKeywords: Column generation; Common problems; Loss functions; Optimization algorithms; Optimization problems; Learning algorithms
dc.titleConvex learning with invariances
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2008
local.identifier.absfor080109 - Pattern Recognition and Data Mining
local.identifier.ariespublicationu8803936xPUB277
local.type.statusPublished Version
local.contributor.affiliationTeo, Choon-Hui, College of Engineering and Computer Science, ANU
local.contributor.affiliationGloberson, Amir, Massachusetts Institute of Technology
local.contributor.affiliationRoweis, Sam, University of Toronto
local.contributor.affiliationSmola, Alexander, College of Engineering and Computer Science, ANU
local.description.embargo2037-12-31
local.bibliographicCitation.startpage1489
local.bibliographicCitation.lastpage1496
dc.date.updated2016-02-24T11:43:59Z
local.identifier.scopusID2-s2.0-84858791159
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Teo_Convex_learning_with_2008.pdf374.38 kBAdobe PDF    Request a copy


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