SVM optimization: Inverse dependence on training set size

Shai Shalev-Shwartz; Nathan Srebro

SVM optimization: Inverse dependence on training set size

Shai Shalev-Shwartz^*
, Nathan Srebro

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

188 Scopus citations

Abstract

We discuss how the runtime of SVM optimization should decrease as the size of the training data increases. We present theoretical and empirical results demonstrating how a simple subgradient descent approach indeed displays such behavior, at least for linear kernels.

Original language	English
Title of host publication	Proceedings of the 25th International Conference on Machine Learning
Pages	928-935
Number of pages	8
State	Published - 2008
Externally published	Yes
Event	25th International Conference on Machine Learning - Helsinki, Finland Duration: 5 Jul 2008 → 9 Jul 2008

Publication series

Name	Proceedings of the 25th International Conference on Machine Learning

Conference

Conference	25th International Conference on Machine Learning
Country/Territory	Finland
City	Helsinki
Period	5/07/08 → 9/07/08

Cite this

@inproceedings{3eb5268cad62433a81b1647af9d8d663,

title = "SVM optimization: Inverse dependence on training set size",

abstract = "We discuss how the runtime of SVM optimization should decrease as the size of the training data increases. We present theoretical and empirical results demonstrating how a simple subgradient descent approach indeed displays such behavior, at least for linear kernels.",

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

year = "2008",

language = "אנגלית",

isbn = "9781605582054",

series = "Proceedings of the 25th International Conference on Machine Learning",

pages = "928--935",

booktitle = "Proceedings of the 25th International Conference on Machine Learning",

note = "25th International Conference on Machine Learning ; Conference date: 05-07-2008 Through 09-07-2008",

}

TY - GEN

T1 - SVM optimization

T2 - 25th International Conference on Machine Learning

AU - Shalev-Shwartz, Shai

AU - Srebro, Nathan

PY - 2008

Y1 - 2008

N2 - We discuss how the runtime of SVM optimization should decrease as the size of the training data increases. We present theoretical and empirical results demonstrating how a simple subgradient descent approach indeed displays such behavior, at least for linear kernels.

AB - We discuss how the runtime of SVM optimization should decrease as the size of the training data increases. We present theoretical and empirical results demonstrating how a simple subgradient descent approach indeed displays such behavior, at least for linear kernels.

UR - https://www.scopus.com/pages/publications/56449110590

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:56449110590

SN - 9781605582054

T3 - Proceedings of the 25th International Conference on Machine Learning

SP - 928

EP - 935

BT - Proceedings of the 25th International Conference on Machine Learning

Y2 - 5 July 2008 through 9 July 2008

ER -

SVM optimization: Inverse dependence on training set size

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this