Skip navigation
Skip navigation

On the limitations of embedding methods

Mendelson, Shahar

Description

We show that for any class of functions H which has a reasonable combinatorial dimension, the vast majority of small subsets of the combinatorial cube can not be represented as a Lipschitz image of a subset of H, unless the Lipschitz constant is very larg

dc.contributor.authorMendelson, Shahar
dc.date.accessioned2015-12-13T23:04:18Z
dc.date.available2015-12-13T23:04:18Z
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/1885/85311
dc.description.abstractWe show that for any class of functions H which has a reasonable combinatorial dimension, the vast majority of small subsets of the combinatorial cube can not be represented as a Lipschitz image of a subset of H, unless the Lipschitz constant is very larg
dc.publisherSpringer
dc.sourceLecture Notes in Computer Science (LNCS)
dc.subjectKeywords: Classification (of information); Problem solving; Classification problems; Combinatorial dimension; Lipschitz image; Lipschitz loss; Embedded systems
dc.titleOn the limitations of embedding methods
dc.typeJournal article
local.description.notesImported from ARIES
local.description.refereedYes
local.identifier.citationvolume3559
dc.date.issued2005
local.identifier.absfor080199 - Artificial Intelligence and Image Processing not elsewhere classified
local.identifier.ariespublicationMigratedxPub13653
local.type.statusPublished Version
local.contributor.affiliationMendelson, Shahar, College of Physical and Mathematical Sciences, ANU
local.bibliographicCitation.startpage353
local.bibliographicCitation.lastpage365
dc.date.updated2015-12-12T07:55:15Z
local.identifier.scopusID2-s2.0-26944468649
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:  17 November 2022/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator