AUC Maximizing Support Vector Learning

Ulf Brefeld; Tobias Scheffer

AUC Maximizing Support Vector Learning

Ulf Brefeld
, Tobias Scheffer

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

Abstract

The area under the ROC curve (AUC) is a natural performance measure when thegoal is to find a discriminative decision function.We present a rigorous derivation of an AUC maximizing Support Vector Machine; its optimization criterion is composed of a convex bound on the AUC and a margin term.
The number of constraints in the optimization problem grows quadratically in the number of examples. We discuss an approximation for large data sets that clusters the constraints. Our experiments show that the AUC maximizing Support Vector Machine does in fact lead to higher AUC values

Original language	English
Title of host publication	ROC Analysis in Machine Learning
Number of pages	8
Publication date	2005
Publication status	Published - 2005
Externally published	Yes
Event	International Conference on Machine Learning - Bonn, Germany Duration: 11.08.2005 → 11.08.2005 Conference number: 22

Research areas and keywords

Informatics
Business informatics

Access to Document

DownloadAccepted author manuscript, 169 KBLicence: In Copyright

http://users.dsic.upv.es/~flip/ROCML2005/papers/brefeldCRC.pdfLicence: In Copyright

Cite this

@inbook{307d495d62404ef68e7ff53d868df96f,

title = "AUC Maximizing Support Vector Learning",

abstract = "The area under the ROC curve (AUC) is a natural performance measure when thegoal is to find a discriminative decision function.We present a rigorous derivation of an AUC maximizing Support Vector Machine; its optimization criterion is composed of a convex bound on the AUC and a margin term. The number of constraints in the optimization problem grows quadratically in the number of examples. We discuss an approximation for large data sets that clusters the constraints. Our experiments show that the AUC maximizing Support Vector Machine does in fact lead to higher AUC values",

keywords = "Informatics, Business informatics",

author = "Ulf Brefeld and Tobias Scheffer",

year = "2005",

language = "English",

booktitle = "ROC Analysis in Machine Learning",

note = "International Conference on Machine Learning ; Conference date: 11-08-2005 Through 11-08-2005",

}

TY - CHAP

T1 - AUC Maximizing Support Vector Learning

AU - Brefeld, Ulf

AU - Scheffer, Tobias

N1 - Conference code: 22

PY - 2005

Y1 - 2005

N2 - The area under the ROC curve (AUC) is a natural performance measure when thegoal is to find a discriminative decision function.We present a rigorous derivation of an AUC maximizing Support Vector Machine; its optimization criterion is composed of a convex bound on the AUC and a margin term. The number of constraints in the optimization problem grows quadratically in the number of examples. We discuss an approximation for large data sets that clusters the constraints. Our experiments show that the AUC maximizing Support Vector Machine does in fact lead to higher AUC values

AB - The area under the ROC curve (AUC) is a natural performance measure when thegoal is to find a discriminative decision function.We present a rigorous derivation of an AUC maximizing Support Vector Machine; its optimization criterion is composed of a convex bound on the AUC and a margin term. The number of constraints in the optimization problem grows quadratically in the number of examples. We discuss an approximation for large data sets that clusters the constraints. Our experiments show that the AUC maximizing Support Vector Machine does in fact lead to higher AUC values

KW - Informatics

KW - Business informatics

M3 - Article in conference proceedings

BT - ROC Analysis in Machine Learning

T2 - International Conference on Machine Learning

Y2 - 11 August 2005 through 11 August 2005

ER -

AUC Maximizing Support Vector Learning

Abstract

Research areas and keywords

Access to Document

Fingerprint

Cite this