Learning optimally sparse support vector machines

Andrew Cotter; Nathan Srebro; Shai Shalev-Shwartz

Learning optimally sparse support vector machines

Andrew Cotter, Nathan Srebro, Shai Shalev-Shwartz

The Rachel and Selim Benin School of Engineering and Computer Science

The Hebrew University of Jerusalem

Research output: Contribution to conference › Paper › peer-review

Abstract

We show how to train SVMs with an optimal guarantee on the number of support vectors (up to constants), and with sample complexity and training runtime bounds matching the best known for kernel SVM optimization (i.e. without any additional asymptotic cost beyond standard SVM training). Our method is simple to implement and works well in practice.

Original language	English
Pages	266-274
Number of pages	9
State	Published - 2013
Event	30th International Conference on Machine Learning, ICML 2013 - Atlanta, GA, United States Duration: 16 Jun 2013 → 21 Jun 2013

Conference

Conference	30th International Conference on Machine Learning, ICML 2013
Country/Territory	United States
City	Atlanta, GA
Period	16/06/13 → 21/06/13

All Science Journal Classification (ASJC) codes

Human-Computer Interaction
Sociology and Political Science

Cite this

@conference{f91421ef47de4f0181e9b6f2281f75d1,

title = "Learning optimally sparse support vector machines",

abstract = "We show how to train SVMs with an optimal guarantee on the number of support vectors (up to constants), and with sample complexity and training runtime bounds matching the best known for kernel SVM optimization (i.e. without any additional asymptotic cost beyond standard SVM training). Our method is simple to implement and works well in practice.",

author = "Andrew Cotter and Nathan Srebro and Shai Shalev-Shwartz",

year = "2013",

language = "الإنجليزيّة",

pages = "266--274",

note = "30th International Conference on Machine Learning, ICML 2013 ; Conference date: 16-06-2013 Through 21-06-2013",

}

TY - CONF

T1 - Learning optimally sparse support vector machines

AU - Cotter, Andrew

AU - Srebro, Nathan

AU - Shalev-Shwartz, Shai

PY - 2013

Y1 - 2013

N2 - We show how to train SVMs with an optimal guarantee on the number of support vectors (up to constants), and with sample complexity and training runtime bounds matching the best known for kernel SVM optimization (i.e. without any additional asymptotic cost beyond standard SVM training). Our method is simple to implement and works well in practice.

AB - We show how to train SVMs with an optimal guarantee on the number of support vectors (up to constants), and with sample complexity and training runtime bounds matching the best known for kernel SVM optimization (i.e. without any additional asymptotic cost beyond standard SVM training). Our method is simple to implement and works well in practice.

UR - http://www.scopus.com/inward/record.url?scp=84897480859&partnerID=8YFLogxK

M3 - محاضرة

SP - 266

EP - 274

T2 - 30th International Conference on Machine Learning, ICML 2013

Y2 - 16 June 2013 through 21 June 2013

ER -

Learning optimally sparse support vector machines

Abstract

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this