Mini-batch primal and dual methods for SVMs

Martin Takáč; Avleen Bijral; Peter Richtárik; Nathan Srebro

Mini-batch primal and dual methods for SVMs

Martin Takáč, Avleen Bijral, Peter Richtárik, Nathan Srebro

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

Abstract

We address the issue of using mini-batches in stochastic optimization of SVMs. We show that the same quantity, the spectral norm of the data, controls the parallelization speedup obtained for both primal stochastic subgradient descent (SGD) and stochastic dual coordinate ascent (SCDA) methods and use it to derive novel variants of mini-batched SDCA. Our guarantees for both methods are expressed in terms of the original nonsmooth primal problem based on the hinge-loss. Copyright 2013 by the author(s).

Original language	English (US)
Title of host publication	30th International Conference on Machine Learning, ICML 2013
Publisher	International Machine Learning Society (IMLS)[email protected]
Pages	2059-2067
Number of pages	9
State	Published - Jan 1 2013
Externally published	Yes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2023-09-25

Cite this

@inproceedings{7bfc7311a2df43e0bb7cb5772d6b3a70,

title = "Mini-batch primal and dual methods for SVMs",

abstract = "We address the issue of using mini-batches in stochastic optimization of SVMs. We show that the same quantity, the spectral norm of the data, controls the parallelization speedup obtained for both primal stochastic subgradient descent (SGD) and stochastic dual coordinate ascent (SCDA) methods and use it to derive novel variants of mini-batched SDCA. Our guarantees for both methods are expressed in terms of the original nonsmooth primal problem based on the hinge-loss. Copyright 2013 by the author(s).",

author = "Martin Tak{\'a}{\v c} and Avleen Bijral and Peter Richt{\'a}rik and Nathan Srebro",

note = "Generated from Scopus record by KAUST IRTS on 2023-09-25",

year = "2013",

month = jan,

day = "1",

language = "English (US)",

pages = "2059--2067",

booktitle = "30th International Conference on Machine Learning, ICML 2013",

publisher = "International Machine Learning Society (IMLS)[email protected]",

}

TY - GEN

T1 - Mini-batch primal and dual methods for SVMs

AU - Takáč, Martin

AU - Bijral, Avleen

AU - Richtárik, Peter

AU - Srebro, Nathan

N1 - Generated from Scopus record by KAUST IRTS on 2023-09-25

PY - 2013/1/1

Y1 - 2013/1/1

N2 - We address the issue of using mini-batches in stochastic optimization of SVMs. We show that the same quantity, the spectral norm of the data, controls the parallelization speedup obtained for both primal stochastic subgradient descent (SGD) and stochastic dual coordinate ascent (SCDA) methods and use it to derive novel variants of mini-batched SDCA. Our guarantees for both methods are expressed in terms of the original nonsmooth primal problem based on the hinge-loss. Copyright 2013 by the author(s).

AB - We address the issue of using mini-batches in stochastic optimization of SVMs. We show that the same quantity, the spectral norm of the data, controls the parallelization speedup obtained for both primal stochastic subgradient descent (SGD) and stochastic dual coordinate ascent (SCDA) methods and use it to derive novel variants of mini-batched SDCA. Our guarantees for both methods are expressed in terms of the original nonsmooth primal problem based on the hinge-loss. Copyright 2013 by the author(s).

UR - http://www.scopus.com/inward/record.url?scp=84897543082&partnerID=8YFLogxK

M3 - Conference contribution

SP - 2059

EP - 2067

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

PB - International Machine Learning Society (IMLS)[email protected]

ER -

Mini-batch primal and dual methods for SVMs

Abstract

Bibliographical note

Other files and links

Fingerprint

Cite this