Multi-objective model selection for support vector machines

Christian Igel

doi:10.1007/978-3-540-31880-4_37

Multi-objective model selection for support vector machines

Christian Igel^*

^*Corresponding author af dette arbejde

44 Citationer (Scopus)

Abstract

In this article, model selection for support vector machines is viewed as a multi-objective optimization problem, where model complexity and training accuracy define two conflicting objectives. Different optimization criteria are evaluated: Split modified radius margin bounds, which allow for comparing existing model selection criteria, and the training error in conjunction with the number of support vectors for designing sparse solutions.

Originalsprog	Engelsk
Titel	Evolutionary Multi-Criterion Optimization : Third International Conference, EMO 2005, Guanajuato, Mexico, March 9-11, 2005. Proceedings
Redaktører	Carlos A. Coello Coello, Arturo Hernándex Aguirre, Eckart Zitzler
Antal sider	13
Forlag	Springer
Publikationsdato	2005
Sider	534-546
ISBN (Trykt)	978-3-540-24983-2
ISBN (Elektronisk)	978-3-540-31880-4
DOI	https://doi.org/10.1007/978-3-540-31880-4_37
Status	Udgivet - 2005
Udgivet eksternt	Ja
Begivenhed	3rd International Conference on Evolutionary Multi-Criterion Optimization - Guanajuato, Mexico Varighed: 9 mar. 2005 → 11 mar. 2005 Konferencens nummer: 3

Konference

Konference	3rd International Conference on Evolutionary Multi-Criterion Optimization
Nummer	3
Land/Område	Mexico
By	Guanajuato
Periode	09/03/2005 → 11/03/2005

Navn	Lecture notes in computer science
Vol/bind	3410
ISSN	0302-9743

Adgang til dokumentet

10.1007/978-3-540-31880-4_37

Citationsformater

Igel, C. (2005). Multi-objective model selection for support vector machines. I C. A. C. Coello, A. H. Aguirre, & E. Zitzler (red.), Evolutionary Multi-Criterion Optimization: Third International Conference, EMO 2005, Guanajuato, Mexico, March 9-11, 2005. Proceedings (s. 534-546). Springer. Lecture notes in computer science Bind 3410 https://doi.org/10.1007/978-3-540-31880-4_37

Multi-objective model selection for support vector machines. / Igel, Christian.

Evolutionary Multi-Criterion Optimization: Third International Conference, EMO 2005, Guanajuato, Mexico, March 9-11, 2005. Proceedings. red. / Carlos A. Coello Coello; Arturo Hernándex Aguirre; Eckart Zitzler. Springer, 2005. s. 534-546 (Lecture notes in computer science, Bind 3410).

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Igel, C 2005, Multi-objective model selection for support vector machines. i CAC Coello, AH Aguirre & E Zitzler (red), Evolutionary Multi-Criterion Optimization: Third International Conference, EMO 2005, Guanajuato, Mexico, March 9-11, 2005. Proceedings. Springer, Lecture notes in computer science, bind 3410, s. 534-546, 3rd International Conference on Evolutionary Multi-Criterion Optimization, Guanajuato, Mexico, 09/03/2005. https://doi.org/10.1007/978-3-540-31880-4_37

@inproceedings{003ec3915b8145649e4c1cb67f48b181,

title = "Multi-objective model selection for support vector machines",

abstract = "In this article, model selection for support vector machines is viewed as a multi-objective optimization problem, where model complexity and training accuracy define two conflicting objectives. Different optimization criteria are evaluated: Split modified radius margin bounds, which allow for comparing existing model selection criteria, and the training error in conjunction with the number of support vectors for designing sparse solutions.",

author = "Christian Igel",

year = "2005",

doi = "10.1007/978-3-540-31880-4_37",

language = "English",

isbn = "978-3-540-24983-2",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "534--546",

editor = "Coello, {Carlos A. Coello} and Aguirre, {Arturo Hern{\'a}ndex} and Eckart Zitzler",

booktitle = "Evolutionary Multi-Criterion Optimization",

note = "3rd International Conference on Evolutionary Multi-Criterion Optimization ; Conference date: 09-03-2005 Through 11-03-2005",

}

TY - GEN

T1 - Multi-objective model selection for support vector machines

AU - Igel, Christian

N1 - Conference code: 3

PY - 2005

Y1 - 2005

N2 - In this article, model selection for support vector machines is viewed as a multi-objective optimization problem, where model complexity and training accuracy define two conflicting objectives. Different optimization criteria are evaluated: Split modified radius margin bounds, which allow for comparing existing model selection criteria, and the training error in conjunction with the number of support vectors for designing sparse solutions.

AB - In this article, model selection for support vector machines is viewed as a multi-objective optimization problem, where model complexity and training accuracy define two conflicting objectives. Different optimization criteria are evaluated: Split modified radius margin bounds, which allow for comparing existing model selection criteria, and the training error in conjunction with the number of support vectors for designing sparse solutions.

U2 - 10.1007/978-3-540-31880-4_37

DO - 10.1007/978-3-540-31880-4_37

M3 - Article in proceedings

AN - SCOPUS:24344435631

SN - 978-3-540-24983-2

T3 - Lecture notes in computer science

SP - 534

EP - 546

BT - Evolutionary Multi-Criterion Optimization

A2 - Coello, Carlos A. Coello

A2 - Aguirre, Arturo Hernándex

A2 - Zitzler, Eckart

PB - Springer

T2 - 3rd International Conference on Evolutionary Multi-Criterion Optimization

Y2 - 9 March 2005 through 11 March 2005

ER -

Multi-objective model selection for support vector machines

Abstract

Konference

Adgang til dokumentet

Fingeraftryk

Citationsformater