Solving ridge regression using sketched preconditioned SVRG

Alon Gonen; Francesco Orabona; Shai Shalev-Shwartz

Solving ridge regression using sketched preconditioned SVRG

Alon Gonen, Francesco Orabona, Shai Shalev-Shwartz

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

Abstract

We develop a novel preconditioning method for ridge regression, based on recent linear sketching methods. By equipping Stochastic Variance Reduced Gradient (SVRG) with this preconditioning process, we obtain a significant speed-up relative to fast stochastic methods such as SVRG, SDCA and SAG.

Original language	English (US)
Title of host publication	33rd International Conference on Machine Learning, ICML 2016
Publisher	International Machine Learning Society (IMLS)[email protected]
Pages	2102-2111
Number of pages	10
ISBN (Print)	9781510829008
State	Published - Jan 1 2016
Externally published	Yes

Bibliographical note

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

Cite this

@inproceedings{f63d600faa234386b3c472e5dd10301d,

title = "Solving ridge regression using sketched preconditioned SVRG",

abstract = "We develop a novel preconditioning method for ridge regression, based on recent linear sketching methods. By equipping Stochastic Variance Reduced Gradient (SVRG) with this preconditioning process, we obtain a significant speed-up relative to fast stochastic methods such as SVRG, SDCA and SAG.",

author = "Alon Gonen and Francesco Orabona and Shai Shalev-Shwartz",

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

year = "2016",

month = jan,

day = "1",

language = "English (US)",

isbn = "9781510829008",

pages = "2102--2111",

booktitle = "33rd International Conference on Machine Learning, ICML 2016",

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

}

TY - GEN

T1 - Solving ridge regression using sketched preconditioned SVRG

AU - Gonen, Alon

AU - Orabona, Francesco

AU - Shalev-Shwartz, Shai

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

PY - 2016/1/1

Y1 - 2016/1/1

N2 - We develop a novel preconditioning method for ridge regression, based on recent linear sketching methods. By equipping Stochastic Variance Reduced Gradient (SVRG) with this preconditioning process, we obtain a significant speed-up relative to fast stochastic methods such as SVRG, SDCA and SAG.

AB - We develop a novel preconditioning method for ridge regression, based on recent linear sketching methods. By equipping Stochastic Variance Reduced Gradient (SVRG) with this preconditioning process, we obtain a significant speed-up relative to fast stochastic methods such as SVRG, SDCA and SAG.

UR - http://www.scopus.com/inward/record.url?scp=84998673804&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781510829008

SP - 2102

EP - 2111

BT - 33rd International Conference on Machine Learning, ICML 2016

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

ER -

Solving ridge regression using sketched preconditioned SVRG

Abstract

Bibliographical note

Other files and links

Fingerprint

Cite this