Skip navigation
Skip navigation
Open Research will be down for maintenance between 8:00 and 8:15 am on Tuesday, December 1 2020.

Random subclass bounds

Mendelson, Shahar; Philips, Petra

Description

It has been recently shown that sharp generalization bounds can be obtained when the function class from which the algorithm chooses its hypotheses is "small" in the sense that the Rademacher averages of this function class are small. Seemingly based on different arguments, generalization bounds were obtained in the compression scheme, luckiness, and algorithmic luckiness frameworks in which the "size" of the function class is not specified a priori. We show that the bounds obtained in all...[Show more]

dc.contributor.authorMendelson, Shahar
dc.contributor.authorPhilips, Petra
dc.coverage.spatialWashington USA
dc.date.accessioned2015-12-13T23:12:22Z
dc.date.available2015-12-13T23:12:22Z
dc.date.createdAugust 24 2003
dc.identifier.isbn3540407200
dc.identifier.urihttp://hdl.handle.net/1885/88023
dc.description.abstractIt has been recently shown that sharp generalization bounds can be obtained when the function class from which the algorithm chooses its hypotheses is "small" in the sense that the Rademacher averages of this function class are small. Seemingly based on different arguments, generalization bounds were obtained in the compression scheme, luckiness, and algorithmic luckiness frameworks in which the "size" of the function class is not specified a priori. We show that the bounds obtained in all these frameworks follow from the same general principle, namely that coordinate projections of this function subclass evaluated on random samples are "small" with high probability.
dc.publisherSpringer
dc.relation.ispartofseriesAnnual Conference on Computational Learning Theory (COLT 2003)
dc.sourceComputational Learning Theory and Kernel Machines, 16th Annual Conference on Computational Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003, Washington DC, USA, August 24-27, 2003
dc.source.urihttp://www.informatik.uni-trier.de/~ley/db/conf/colt
dc.titleRandom subclass bounds
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2003
local.identifier.absfor080614 - Pacific Peoples Information and Knowledge Systems
local.identifier.ariespublicationMigratedxPub17531
local.type.statusPublished Version
local.contributor.affiliationMendelson, Shahar, College of Engineering and Computer Science, ANU
local.contributor.affiliationPhilips, Petra, College of Engineering and Computer Science, ANU
local.bibliographicCitation.startpage1
local.bibliographicCitation.lastpage17
dc.date.updated2015-12-12T08:31:21Z
local.identifier.scopusID2-s2.0-9444278349
CollectionsANU Research Publications

Download

There are no files associated with this item.


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