Stochastic variance reduced optimization for nonconvex sparse learning

Xingguo Li; Tuo Zhao; Raman Arora; Han Liu; Jarvis Haupt

Stochastic variance reduced optimization for nonconvex sparse learning

Xingguo Li, Tuo Zhao, Raman Arora, Han Liu, Jarvis Haupt

Electrical and Computer Engineering

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

15 Scopus citations

Abstract

We propose a stochastic variance reduced optimization algorithm for solving a class of largescale nonconvex optimization problems with cardinality constraints, and provide sufficient conditions under which the proposed algorithm enjoys strong linear convergence guarantees and optimal estimation accuracy in high dimensions. Numerical experiments demonstrate the efficiency of our method in terms of both parameter estimation and computational performance.

Original language	English (US)
Title of host publication	33rd International Conference on Machine Learning, ICML 2016
Editors	Maria Florina Balcan, Kilian Q. Weinberger
Publisher	International Machine Learning Society (IMLS)
Pages	1448-1460
Number of pages	13
ISBN (Electronic)	9781510829008
State	Published - 2016
Event	33rd International Conference on Machine Learning, ICML 2016 - New York City, United States Duration: Jun 19 2016 → Jun 24 2016

Publication series

Name	33rd International Conference on Machine Learning, ICML 2016
Volume	2

Other

Other	33rd International Conference on Machine Learning, ICML 2016
Country/Territory	United States
City	New York City
Period	6/19/16 → 6/24/16

Bibliographical note

Funding Information:
This research is supported by NSF CCF-1217751; NSF AST-1247885; DARPA Young Faculty Award N66001-14-1-4047; NSF DMS-1454377-CAREER; NSF IIS-1546482-BIGDATA; NIH R01MH102339; NSF IIS-1408910; NSFIIS-1332109; NIH R01GM083084.

OpenUrl availability

Full text

Cite this

Li, X., Zhao, T., Arora, R., Liu, H., & Haupt, J. (2016). Stochastic variance reduced optimization for nonconvex sparse learning. In M. F. Balcan, & K. Q. Weinberger (Eds.), 33rd International Conference on Machine Learning, ICML 2016 (pp. 1448-1460). (33rd International Conference on Machine Learning, ICML 2016; Vol. 2). International Machine Learning Society (IMLS).

Stochastic variance reduced optimization for nonconvex sparse learning. / Li, Xingguo; Zhao, Tuo; Arora, Raman et al.
33rd International Conference on Machine Learning, ICML 2016. ed. / Maria Florina Balcan; Kilian Q. Weinberger. International Machine Learning Society (IMLS), 2016. p. 1448-1460 (33rd International Conference on Machine Learning, ICML 2016; Vol. 2).

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

Li, X, Zhao, T, Arora, R, Liu, H & Haupt, J 2016, Stochastic variance reduced optimization for nonconvex sparse learning. in MF Balcan & KQ Weinberger (eds), 33rd International Conference on Machine Learning, ICML 2016. 33rd International Conference on Machine Learning, ICML 2016, vol. 2, International Machine Learning Society (IMLS), pp. 1448-1460, 33rd International Conference on Machine Learning, ICML 2016, New York City, United States, 6/19/16.

@inproceedings{4df60f3e77eb40678d32cfaece90da93,

title = "Stochastic variance reduced optimization for nonconvex sparse learning",

abstract = "We propose a stochastic variance reduced optimization algorithm for solving a class of largescale nonconvex optimization problems with cardinality constraints, and provide sufficient conditions under which the proposed algorithm enjoys strong linear convergence guarantees and optimal estimation accuracy in high dimensions. Numerical experiments demonstrate the efficiency of our method in terms of both parameter estimation and computational performance.",

author = "Xingguo Li and Tuo Zhao and Raman Arora and Han Liu and Jarvis Haupt",

note = "Funding Information: This research is supported by NSF CCF-1217751; NSF AST-1247885; DARPA Young Faculty Award N66001-14-1-4047; NSF DMS-1454377-CAREER; NSF IIS-1546482-BIGDATA; NIH R01MH102339; NSF IIS-1408910; NSFIIS-1332109; NIH R01GM083084.; 33rd International Conference on Machine Learning, ICML 2016 ; Conference date: 19-06-2016 Through 24-06-2016",

year = "2016",

language = "English (US)",

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

publisher = "International Machine Learning Society (IMLS)",

pages = "1448--1460",

editor = "Balcan, {Maria Florina} and Weinberger, {Kilian Q.}",

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

}

TY - GEN

T1 - Stochastic variance reduced optimization for nonconvex sparse learning

AU - Li, Xingguo

AU - Zhao, Tuo

AU - Arora, Raman

AU - Liu, Han

AU - Haupt, Jarvis

N1 - Funding Information: This research is supported by NSF CCF-1217751; NSF AST-1247885; DARPA Young Faculty Award N66001-14-1-4047; NSF DMS-1454377-CAREER; NSF IIS-1546482-BIGDATA; NIH R01MH102339; NSF IIS-1408910; NSFIIS-1332109; NIH R01GM083084.

PY - 2016

Y1 - 2016

N2 - We propose a stochastic variance reduced optimization algorithm for solving a class of largescale nonconvex optimization problems with cardinality constraints, and provide sufficient conditions under which the proposed algorithm enjoys strong linear convergence guarantees and optimal estimation accuracy in high dimensions. Numerical experiments demonstrate the efficiency of our method in terms of both parameter estimation and computational performance.

AB - We propose a stochastic variance reduced optimization algorithm for solving a class of largescale nonconvex optimization problems with cardinality constraints, and provide sufficient conditions under which the proposed algorithm enjoys strong linear convergence guarantees and optimal estimation accuracy in high dimensions. Numerical experiments demonstrate the efficiency of our method in terms of both parameter estimation and computational performance.

UR - http://www.scopus.com/inward/record.url?scp=84998812114&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84998812114&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84998812114

T3 - 33rd International Conference on Machine Learning, ICML 2016

SP - 1448

EP - 1460

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

A2 - Balcan, Maria Florina

A2 - Weinberger, Kilian Q.

PB - International Machine Learning Society (IMLS)

T2 - 33rd International Conference on Machine Learning, ICML 2016

Y2 - 19 June 2016 through 24 June 2016

ER -

Stochastic variance reduced optimization for nonconvex sparse learning

Abstract

Publication series

Other

Bibliographical note

OpenUrl availability

Other files and links

Fingerprint

Cite this