Serveur d'exploration sur l'opéra

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

Local Rademacher Complexity: sharper risk bounds with and without unlabeled samples.

Identifieur interne : 000102 ( PubMed/Corpus ); précédent : 000101; suivant : 000103

Local Rademacher Complexity: sharper risk bounds with and without unlabeled samples.

Auteurs : Luca Oneto ; Alessandro Ghio ; Sandro Ridella ; Davide Anguita

Source :

RBID : pubmed:25734890

English descriptors

Abstract

We derive in this paper a new Local Rademacher Complexity risk bound on the generalization ability of a model, which is able to take advantage of the availability of unlabeled samples. Moreover, this new bound improves state-of-the-art results even when no unlabeled samples are available.

DOI: 10.1016/j.neunet.2015.02.006
PubMed: 25734890

Links to Exploration step

pubmed:25734890

Le document en format XML

<record>
<TEI>
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="en">Local Rademacher Complexity: sharper risk bounds with and without unlabeled samples.</title>
<author>
<name sortKey="Oneto, Luca" sort="Oneto, Luca" uniqKey="Oneto L" first="Luca" last="Oneto">Luca Oneto</name>
<affiliation>
<nlm:affiliation>DITEN - University of Genova, Via Opera Pia 11A, I-16145 Genova, Italy. Electronic address: Luca.Oneto@unige.it.</nlm:affiliation>
</affiliation>
</author>
<author>
<name sortKey="Ghio, Alessandro" sort="Ghio, Alessandro" uniqKey="Ghio A" first="Alessandro" last="Ghio">Alessandro Ghio</name>
<affiliation>
<nlm:affiliation>DIBRIS - University of Genova, Via Opera Pia 13, I-16145 Genova, Italy. Electronic address: Alessandro.Ghio@unige.it.</nlm:affiliation>
</affiliation>
</author>
<author>
<name sortKey="Ridella, Sandro" sort="Ridella, Sandro" uniqKey="Ridella S" first="Sandro" last="Ridella">Sandro Ridella</name>
<affiliation>
<nlm:affiliation>DITEN - University of Genova, Via Opera Pia 11A, I-16145 Genova, Italy. Electronic address: Sandro.Ridella@unige.it.</nlm:affiliation>
</affiliation>
</author>
<author>
<name sortKey="Anguita, Davide" sort="Anguita, Davide" uniqKey="Anguita D" first="Davide" last="Anguita">Davide Anguita</name>
<affiliation>
<nlm:affiliation>DIBRIS - University of Genova, Via Opera Pia 13, I-16145 Genova, Italy. Electronic address: Davide.Anguita@unige.it.</nlm:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt>
<idno type="wicri:source">PubMed</idno>
<date when="2015">2015</date>
<idno type="RBID">pubmed:25734890</idno>
<idno type="pmid">25734890</idno>
<idno type="doi">10.1016/j.neunet.2015.02.006</idno>
<idno type="wicri:Area/PubMed/Corpus">000102</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title xml:lang="en">Local Rademacher Complexity: sharper risk bounds with and without unlabeled samples.</title>
<author>
<name sortKey="Oneto, Luca" sort="Oneto, Luca" uniqKey="Oneto L" first="Luca" last="Oneto">Luca Oneto</name>
<affiliation>
<nlm:affiliation>DITEN - University of Genova, Via Opera Pia 11A, I-16145 Genova, Italy. Electronic address: Luca.Oneto@unige.it.</nlm:affiliation>
</affiliation>
</author>
<author>
<name sortKey="Ghio, Alessandro" sort="Ghio, Alessandro" uniqKey="Ghio A" first="Alessandro" last="Ghio">Alessandro Ghio</name>
<affiliation>
<nlm:affiliation>DIBRIS - University of Genova, Via Opera Pia 13, I-16145 Genova, Italy. Electronic address: Alessandro.Ghio@unige.it.</nlm:affiliation>
</affiliation>
</author>
<author>
<name sortKey="Ridella, Sandro" sort="Ridella, Sandro" uniqKey="Ridella S" first="Sandro" last="Ridella">Sandro Ridella</name>
<affiliation>
<nlm:affiliation>DITEN - University of Genova, Via Opera Pia 11A, I-16145 Genova, Italy. Electronic address: Sandro.Ridella@unige.it.</nlm:affiliation>
</affiliation>
</author>
<author>
<name sortKey="Anguita, Davide" sort="Anguita, Davide" uniqKey="Anguita D" first="Davide" last="Anguita">Davide Anguita</name>
<affiliation>
<nlm:affiliation>DIBRIS - University of Genova, Via Opera Pia 13, I-16145 Genova, Italy. Electronic address: Davide.Anguita@unige.it.</nlm:affiliation>
</affiliation>
</author>
</analytic>
<series>
<title level="j">Neural networks : the official journal of the International Neural Network Society</title>
<idno type="e-ISSN">1879-2782</idno>
<imprint>
<date when="2015" type="published">2015</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc>
<textClass>
<keywords scheme="KwdEn" xml:lang="en">
<term>Artificial Intelligence</term>
<term>Models, Statistical</term>
</keywords>
<keywords scheme="MESH" xml:lang="en">
<term>Artificial Intelligence</term>
<term>Models, Statistical</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en">We derive in this paper a new Local Rademacher Complexity risk bound on the generalization ability of a model, which is able to take advantage of the availability of unlabeled samples. Moreover, this new bound improves state-of-the-art results even when no unlabeled samples are available.</div>
</front>
</TEI>
<pubmed>
<MedlineCitation Owner="NLM" Status="MEDLINE">
<PMID Version="1">25734890</PMID>
<DateCreated>
<Year>2015</Year>
<Month>03</Month>
<Day>16</Day>
</DateCreated>
<DateCompleted>
<Year>2015</Year>
<Month>07</Month>
<Day>07</Day>
</DateCompleted>
<Article PubModel="Print-Electronic">
<Journal>
<ISSN IssnType="Electronic">1879-2782</ISSN>
<JournalIssue CitedMedium="Internet">
<Volume>65</Volume>
<PubDate>
<Year>2015</Year>
<Month>May</Month>
</PubDate>
</JournalIssue>
<Title>Neural networks : the official journal of the International Neural Network Society</Title>
<ISOAbbreviation>Neural Netw</ISOAbbreviation>
</Journal>
<ArticleTitle>Local Rademacher Complexity: sharper risk bounds with and without unlabeled samples.</ArticleTitle>
<Pagination>
<MedlinePgn>115-25</MedlinePgn>
</Pagination>
<ELocationID EIdType="doi" ValidYN="Y">10.1016/j.neunet.2015.02.006</ELocationID>
<ELocationID EIdType="pii" ValidYN="Y">S0893-6080(15)00040-4</ELocationID>
<Abstract>
<AbstractText>We derive in this paper a new Local Rademacher Complexity risk bound on the generalization ability of a model, which is able to take advantage of the availability of unlabeled samples. Moreover, this new bound improves state-of-the-art results even when no unlabeled samples are available.</AbstractText>
<CopyrightInformation>Copyright © 2015 Elsevier Ltd. All rights reserved.</CopyrightInformation>
</Abstract>
<AuthorList CompleteYN="Y">
<Author ValidYN="Y">
<LastName>Oneto</LastName>
<ForeName>Luca</ForeName>
<Initials>L</Initials>
<AffiliationInfo>
<Affiliation>DITEN - University of Genova, Via Opera Pia 11A, I-16145 Genova, Italy. Electronic address: Luca.Oneto@unige.it.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y">
<LastName>Ghio</LastName>
<ForeName>Alessandro</ForeName>
<Initials>A</Initials>
<AffiliationInfo>
<Affiliation>DIBRIS - University of Genova, Via Opera Pia 13, I-16145 Genova, Italy. Electronic address: Alessandro.Ghio@unige.it.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y">
<LastName>Ridella</LastName>
<ForeName>Sandro</ForeName>
<Initials>S</Initials>
<AffiliationInfo>
<Affiliation>DITEN - University of Genova, Via Opera Pia 11A, I-16145 Genova, Italy. Electronic address: Sandro.Ridella@unige.it.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y">
<LastName>Anguita</LastName>
<ForeName>Davide</ForeName>
<Initials>D</Initials>
<AffiliationInfo>
<Affiliation>DIBRIS - University of Genova, Via Opera Pia 13, I-16145 Genova, Italy. Electronic address: Davide.Anguita@unige.it.</Affiliation>
</AffiliationInfo>
</Author>
</AuthorList>
<Language>eng</Language>
<PublicationTypeList>
<PublicationType UI="D016428">Journal Article</PublicationType>
</PublicationTypeList>
<ArticleDate DateType="Electronic">
<Year>2015</Year>
<Month>02</Month>
<Day>16</Day>
</ArticleDate>
</Article>
<MedlineJournalInfo>
<Country>United States</Country>
<MedlineTA>Neural Netw</MedlineTA>
<NlmUniqueID>8805018</NlmUniqueID>
<ISSNLinking>0893-6080</ISSNLinking>
</MedlineJournalInfo>
<CitationSubset>IM</CitationSubset>
<MeshHeadingList>
<MeshHeading>
<DescriptorName MajorTopicYN="Y" UI="D001185">Artificial Intelligence</DescriptorName>
</MeshHeading>
<MeshHeading>
<DescriptorName MajorTopicYN="Y" UI="D015233">Models, Statistical</DescriptorName>
</MeshHeading>
</MeshHeadingList>
<KeywordList Owner="NOTNLM">
<Keyword MajorTopicYN="N">Local Rademacher Complexity</Keyword>
<Keyword MajorTopicYN="N">Performance estimation</Keyword>
<Keyword MajorTopicYN="N">Statistical learning theory</Keyword>
<Keyword MajorTopicYN="N">Unlabeled samples</Keyword>
</KeywordList>
</MedlineCitation>
<PubmedData>
<History>
<PubMedPubDate PubStatus="received">
<Year>2014</Year>
<Month>10</Month>
<Day>23</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="accepted">
<Year>2015</Year>
<Month>2</Month>
<Day>4</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="aheadofprint">
<Year>2015</Year>
<Month>2</Month>
<Day>16</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="entrez">
<Year>2015</Year>
<Month>3</Month>
<Day>4</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="pubmed">
<Year>2015</Year>
<Month>3</Month>
<Day>4</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="medline">
<Year>2015</Year>
<Month>7</Month>
<Day>8</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
</History>
<PublicationStatus>ppublish</PublicationStatus>
<ArticleIdList>
<ArticleId IdType="pubmed">25734890</ArticleId>
<ArticleId IdType="pii">S0893-6080(15)00040-4</ArticleId>
<ArticleId IdType="doi">10.1016/j.neunet.2015.02.006</ArticleId>
</ArticleIdList>
</PubmedData>
</pubmed>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/OperaV1/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000102 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000102 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Musique
   |area=    OperaV1
   |flux=    PubMed
   |étape=   Corpus
   |type=    RBID
   |clé=     pubmed:25734890
   |texte=   Local Rademacher Complexity: sharper risk bounds with and without unlabeled samples.
}}

Pour générer des pages wiki

HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i   -Sk "pubmed:25734890" \
       | HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd   \
       | NlmPubMed2Wicri -a OperaV1 

Wicri

This area was generated with Dilib version V0.6.21.
Data generation: Thu Apr 14 14:59:05 2016. Site generation: Thu Oct 8 06:48:41 2020