InforLorV4, PascalFrancis, Corpus, bibRecord, 000220

Sample Complexity of Classifiers Taking Values in Q, Application to Multi-Class SVMs

Identifieur interne : 000220 ( PascalFrancis/Corpus ); précédent : 000219; suivant : 000221

Sample Complexity of Classifiers Taking Values in Q, Application to Multi-Class SVMs

Auteurs : Yann Guermeur

Source :

Communications in statistics. Theory and methods [ 0361-0926 ] ; 2010.

RBID : Pascal:10-0196444

Descripteurs français

Pascal (Inist)
- Analyse multivariable, Analyse discriminante, Théorie statistique, Apprentissage, Méthode statistique, 60J20, Classification automatique(statistiques), 62H30.

English descriptors

KwdEn :
- Discriminant analysis, Learning, Multivariate analysis, Statistical method, Statistical theory.

Abstract

Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such " VC dimensions" exist for models taking values in {0,1}, [1,Q], and . We introduce the generalizations appropriate for the missing case, the one of models with values in ^Q. This provides us with a new guaranteed risk for M-SVMs. For those models, a sharper bound is obtained by using the Rademacher complexity.

Notice en format standard (ISO 2709)

Pour connaître la documentation sur le format Inist Standard.

A01	`01`	`1`		`@0 0361-0926`
A02	`01`			`@0 CSTMDC`
A03		`1`		`@0 Commun. stat., Theory methods`
A05				`@2 39`
A06				`@2 3-5`
A08	`01`	`1`	`ENG`	`@1 Sample Complexity of Classifiers Taking Values in <double-struck R> ^Q, Application to Multi-Class SVMs`
A11	`01`	`1`		`@1 GUERMEUR (Yann)`
A14	`01`			`@1 LORIA-CNRS, Campus Scientifique @2 Vandœuvre-lès-Nancy @3 FRA @Z 1 aut.`
A20				`@1 543-557`
A21				`@1 2010`
A23	`01`			`@0 ENG`
A43	`01`			`@1 INIST @2 16531A @5 354000181965690150`
A44				`@0 0000 @1 © 2010 INIST-CNRS. All rights reserved.`
A45				`@0 3/4 p.`
A47	`01`	`1`		`@0 10-0196444`
A60				`@1 P @2 C`
A61				`@0 A`
A64	`01`	`1`		`@0 Communications in statistics. Theory and methods`
A66	`01`			`@0 USA`
C01	`01`		`ENG`	@0 Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such " VC dimensions" exist for models taking values in {0,1}, [1,Q], and <double-struck R>. We introduce the generalizations appropriate for the missing case, the one of models with values in <double-struck R> ^Q. This provides us with a new guaranteed risk for M-SVMs. For those models, a sharper bound is obtained by using the Rademacher complexity.
C02	`01`	`X`		`@0 001A02H02A`
C02	`02`	`X`		`@0 001A02H01J`
C02	`03`	`X`		`@0 001A02H02I`
C03	`01`	`X`	`FRE`	`@0 Analyse multivariable @5 01`
C03	`01`	`X`	`ENG`	`@0 Multivariate analysis @5 01`
C03	`01`	`X`	`SPA`	`@0 Análisis multivariable @5 01`
C03	`02`	`X`	`FRE`	`@0 Analyse discriminante @5 02`
C03	`02`	`X`	`ENG`	`@0 Discriminant analysis @5 02`
C03	`02`	`X`	`SPA`	`@0 Análisis discriminante @5 02`
C03	`03`	`X`	`FRE`	`@0 Théorie statistique @5 17`
C03	`03`	`X`	`ENG`	`@0 Statistical theory @5 17`
C03	`03`	`X`	`SPA`	`@0 Teoría estadística @5 17`
C03	`04`	`X`	`FRE`	`@0 Apprentissage @5 18`
C03	`04`	`X`	`ENG`	`@0 Learning @5 18`
C03	`04`	`X`	`SPA`	`@0 Aprendizaje @5 18`
C03	`05`	`X`	`FRE`	`@0 Méthode statistique @5 19`
C03	`05`	`X`	`ENG`	`@0 Statistical method @5 19`
C03	`05`	`X`	`SPA`	`@0 Método estadístico @5 19`
C03	`06`	`X`	`FRE`	`@0 60J20 @4 INC @5 70`
C03	`07`	`X`	`FRE`	`@0 Classification automatique(statistiques) @4 INC @5 71`
C03	`08`	`X`	`FRE`	`@0 62H30 @4 INC @5 72`
N21				`@1 130`
N44	`01`			`@1 OTO`
N82				`@1 OTO`

A30	`01`	`1`	`ENG`	`@1 Conference on Applied Stochastic Models and Data Analysis (ASMDA) @2 12 @3 Chania, Crete GRC @4 2007-05-29`

Format Inist (serveur)

NO :	PASCAL 10-0196444 INIST
ET :	Sample Complexity of Classifiers Taking Values in <double-struck R> ^Q, Application to Multi-Class SVMs
AU :	GUERMEUR (Yann)
AF :	LORIA-CNRS, Campus Scientifique/Vandœuvre-lès-Nancy/France (1 aut.)
DT :	Publication en série; Congrès; Niveau analytique
SO :	Communications in statistics. Theory and methods; ISSN 0361-0926; Coden CSTMDC; Etats-Unis; Da. 2010; Vol. 39; No. 3-5; Pp. 543-557; Bibl. 3/4 p.
LA :	Anglais
EA :	Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such " VC dimensions" exist for models taking values in {0,1}, [1,Q], and <double-struck R>. We introduce the generalizations appropriate for the missing case, the one of models with values in <double-struck R> ^Q. This provides us with a new guaranteed risk for M-SVMs. For those models, a sharper bound is obtained by using the Rademacher complexity.
CC :	001A02H02A; 001A02H01J; 001A02H02I
FD :	Analyse multivariable; Analyse discriminante; Théorie statistique; Apprentissage; Méthode statistique; 60J20; Classification automatique(statistiques); 62H30
ED :	Multivariate analysis; Discriminant analysis; Statistical theory; Learning; Statistical method
SD :	Análisis multivariable; Análisis discriminante; Teoría estadística; Aprendizaje; Método estadístico
LO :	INIST-16531A.354000181965690150
ID :	10-0196444

Links to Exploration step

Pascal:10-0196444

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Sample Complexity of Classifiers Taking Values in  <sup>Q</sup>
, Application to Multi-Class SVMs</title>
<author><name sortKey="Guermeur, Yann" sort="Guermeur, Yann" uniqKey="Guermeur Y" first="Yann" last="Guermeur">Yann Guermeur</name>
<affiliation><inist:fA14 i1="01"><s1>LORIA-CNRS, Campus Scientifique</s1>
<s2>Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">10-0196444</idno>
<date when="2010">2010</date>
<idno type="stanalyst">PASCAL 10-0196444 INIST</idno>
<idno type="RBID">Pascal:10-0196444</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000220</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Sample Complexity of Classifiers Taking Values in  <sup>Q</sup>
, Application to Multi-Class SVMs</title>
<author><name sortKey="Guermeur, Yann" sort="Guermeur, Yann" uniqKey="Guermeur Y" first="Yann" last="Guermeur">Yann Guermeur</name>
<affiliation><inist:fA14 i1="01"><s1>LORIA-CNRS, Campus Scientifique</s1>
<s2>Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Communications in statistics. Theory and methods</title>
<title level="j" type="abbreviated">Commun. stat., Theory methods</title>
<idno type="ISSN">0361-0926</idno>
<imprint><date when="2010">2010</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Communications in statistics. Theory and methods</title>
<title level="j" type="abbreviated">Commun. stat., Theory methods</title>
<idno type="ISSN">0361-0926</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Discriminant analysis</term>
<term>Learning</term>
<term>Multivariate analysis</term>
<term>Statistical method</term>
<term>Statistical theory</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Analyse multivariable</term>
<term>Analyse discriminante</term>
<term>Théorie statistique</term>
<term>Apprentissage</term>
<term>Méthode statistique</term>
<term>60J20</term>
<term>Classification automatique(statistiques)</term>
<term>62H30</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such " VC dimensions" exist for models taking values in {0,1}, [1,Q], and . We introduce the generalizations appropriate for the missing case, the one of models with values in  <sup>Q</sup>
. This provides us with a new guaranteed risk for M-SVMs. For those models, a sharper bound is obtained by using the Rademacher complexity.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0361-0926</s0>
</fA01>
<fA02 i1="01"><s0>CSTMDC</s0>
</fA02>
<fA03 i2="1"><s0>Commun. stat., Theory methods</s0>
</fA03>
<fA05><s2>39</s2>
</fA05>
<fA06><s2>3-5</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>Sample Complexity of Classifiers Taking Values in  <sup>Q</sup>
, Application to Multi-Class SVMs</s1>
</fA08>
<fA11 i1="01" i2="1"><s1>GUERMEUR (Yann)</s1>
</fA11>
<fA14 i1="01"><s1>LORIA-CNRS, Campus Scientifique</s1>
<s2>Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</fA14>
<fA20><s1>543-557</s1>
</fA20>
<fA21><s1>2010</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>16531A</s2>
<s5>354000181965690150</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2010 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>3/4 p.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>10-0196444</s0>
</fA47>
<fA60><s1>P</s1>
<s2>C</s2>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>Communications in statistics. Theory and methods</s0>
</fA64>
<fA66 i1="01"><s0>USA</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such " VC dimensions" exist for models taking values in {0,1}, [1,Q], and . We introduce the generalizations appropriate for the missing case, the one of models with values in  <sup>Q</sup>
. This provides us with a new guaranteed risk for M-SVMs. For those models, a sharper bound is obtained by using the Rademacher complexity.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001A02H02A</s0>
</fC02>
<fC02 i1="02" i2="X"><s0>001A02H01J</s0>
</fC02>
<fC02 i1="03" i2="X"><s0>001A02H02I</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Analyse multivariable</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Multivariate analysis</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Análisis multivariable</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Analyse discriminante</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Discriminant analysis</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Análisis discriminante</s0>
<s5>02</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Théorie statistique</s0>
<s5>17</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Statistical theory</s0>
<s5>17</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Teoría estadística</s0>
<s5>17</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Apprentissage</s0>
<s5>18</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Learning</s0>
<s5>18</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Aprendizaje</s0>
<s5>18</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Méthode statistique</s0>
<s5>19</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Statistical method</s0>
<s5>19</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Método estadístico</s0>
<s5>19</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>60J20</s0>
<s4>INC</s4>
<s5>70</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Classification automatique(statistiques)</s0>
<s4>INC</s4>
<s5>71</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>62H30</s0>
<s4>INC</s4>
<s5>72</s5>
</fC03>
<fN21><s1>130</s1>
</fN21>
<fN44 i1="01"><s1>OTO</s1>
</fN44>
<fN82><s1>OTO</s1>
</fN82>
</pA>
<pR><fA30 i1="01" i2="1" l="ENG"><s1>Conference on Applied Stochastic Models and Data Analysis (ASMDA)</s1>
<s2>12</s2>
<s3>Chania, Crete GRC</s3>
<s4>2007-05-29</s4>
</fA30>
</pR>
</standard>
<server><NO>PASCAL 10-0196444 INIST</NO>
<ET>Sample Complexity of Classifiers Taking Values in  <sup>Q</sup>
, Application to Multi-Class SVMs</ET>
<AU>GUERMEUR (Yann)</AU>
<AF>LORIA-CNRS, Campus Scientifique/Vandœuvre-lès-Nancy/France (1 aut.)</AF>
<DT>Publication en série; Congrès; Niveau analytique</DT>
<SO>Communications in statistics. Theory and methods; ISSN 0361-0926; Coden CSTMDC; Etats-Unis; Da. 2010; Vol. 39; No. 3-5; Pp. 543-557; Bibl. 3/4 p.</SO>
<LA>Anglais</LA>
<EA>Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such " VC dimensions" exist for models taking values in {0,1}, [1,Q], and . We introduce the generalizations appropriate for the missing case, the one of models with values in  <sup>Q</sup>
. This provides us with a new guaranteed risk for M-SVMs. For those models, a sharper bound is obtained by using the Rademacher complexity.</EA>
<CC>001A02H02A; 001A02H01J; 001A02H02I</CC>
<FD>Analyse multivariable; Analyse discriminante; Théorie statistique; Apprentissage; Méthode statistique; 60J20; Classification automatique(statistiques); 62H30</FD>
<ED>Multivariate analysis; Discriminant analysis; Statistical theory; Learning; Statistical method</ED>
<SD>Análisis multivariable; Análisis discriminante; Teoría estadística; Aprendizaje; Método estadístico</SD>
<LO>INIST-16531A.354000181965690150</LO>
<ID>10-0196444</ID>
</server>
</inist>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/PascalFrancis/Corpus

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000220 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000220 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Lorraine
   |area=    InforLorV4
   |flux=    PascalFrancis
   |étape=   Corpus
   |type=    RBID
   |clé=     Pascal:10-0196444
   |texte=   Sample Complexity of Classifiers Taking Values in  Q, Application to Multi-Class SVMs
}}

This area was generated with Dilib version V0.6.33.
Data generation: Mon Jun 10 21:56:28 2019. Site generation: Fri Feb 25 15:29:27 2022

	Serveur d'exploration sur la recherche en informatique en Lorraine
	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.

Serveur d'exploration sur la recherche en informatique en Lorraine

Sample Complexity of Classifiers Taking Values in Q, Application to Multi-Class SVMs

Sample Complexity of Classifiers Taking Values in Q, Application to Multi-Class SVMs

Source :

Descripteurs français

English descriptors

Abstract

Notice en format standard (ISO 2709)

Format Inist (serveur)

Links to Exploration step

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri