Efficient Euclidean projections in linear time

Jun Liu, Jieping Ye

Research output: Chapter in Book/Report/Conference proceedingConference contribution

99 Citations (Scopus)

Abstract

We consider the problem of computing the Euclidean projection of a vector of length n onto a closed convex set including the ℓ1 and the specialized polyhedra employed in (Shalev-Shwartz & Singer, 2006). These problems have played building block roles in solving several ℓ1-norm based sparse learning problems. Existing methods have a worst-case time complexity of O(n log n). In this paper, we propose to cast both Euclidean projections as root finding problems associated with specific auxiliary functions, which can be solved in linear time via bisection. We further make use of the special structure of the auxiliary functions, and propose an improved bisection algorithm. Empirical studies demonstrate that the proposed algorithms are much more efficient than the competing ones for computing the projections.

Original languageEnglish (US)
Title of host publicationProceedings of the 26th International Conference On Machine Learning, ICML 2009
Pages657-664
Number of pages8
StatePublished - 2009
Event26th International Conference On Machine Learning, ICML 2009 - Montreal, QC, Canada
Duration: Jun 14 2009Jun 18 2009

Other

Other26th International Conference On Machine Learning, ICML 2009
CountryCanada
CityMontreal, QC
Period6/14/096/18/09

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Software

Cite this

Liu, J., & Ye, J. (2009). Efficient Euclidean projections in linear time. In Proceedings of the 26th International Conference On Machine Learning, ICML 2009 (pp. 657-664)

Efficient Euclidean projections in linear time. / Liu, Jun; Ye, Jieping.

Proceedings of the 26th International Conference On Machine Learning, ICML 2009. 2009. p. 657-664.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, J & Ye, J 2009, Efficient Euclidean projections in linear time. in Proceedings of the 26th International Conference On Machine Learning, ICML 2009. pp. 657-664, 26th International Conference On Machine Learning, ICML 2009, Montreal, QC, Canada, 6/14/09.
Liu J, Ye J. Efficient Euclidean projections in linear time. In Proceedings of the 26th International Conference On Machine Learning, ICML 2009. 2009. p. 657-664
Liu, Jun ; Ye, Jieping. / Efficient Euclidean projections in linear time. Proceedings of the 26th International Conference On Machine Learning, ICML 2009. 2009. pp. 657-664
@inproceedings{9d3cdb243f96401386a5801650c970d5,
title = "Efficient Euclidean projections in linear time",
abstract = "We consider the problem of computing the Euclidean projection of a vector of length n onto a closed convex set including the ℓ1 and the specialized polyhedra employed in (Shalev-Shwartz & Singer, 2006). These problems have played building block roles in solving several ℓ1-norm based sparse learning problems. Existing methods have a worst-case time complexity of O(n log n). In this paper, we propose to cast both Euclidean projections as root finding problems associated with specific auxiliary functions, which can be solved in linear time via bisection. We further make use of the special structure of the auxiliary functions, and propose an improved bisection algorithm. Empirical studies demonstrate that the proposed algorithms are much more efficient than the competing ones for computing the projections.",
author = "Jun Liu and Jieping Ye",
year = "2009",
language = "English (US)",
isbn = "9781605585161",
pages = "657--664",
booktitle = "Proceedings of the 26th International Conference On Machine Learning, ICML 2009",

}

TY - GEN

T1 - Efficient Euclidean projections in linear time

AU - Liu, Jun

AU - Ye, Jieping

PY - 2009

Y1 - 2009

N2 - We consider the problem of computing the Euclidean projection of a vector of length n onto a closed convex set including the ℓ1 and the specialized polyhedra employed in (Shalev-Shwartz & Singer, 2006). These problems have played building block roles in solving several ℓ1-norm based sparse learning problems. Existing methods have a worst-case time complexity of O(n log n). In this paper, we propose to cast both Euclidean projections as root finding problems associated with specific auxiliary functions, which can be solved in linear time via bisection. We further make use of the special structure of the auxiliary functions, and propose an improved bisection algorithm. Empirical studies demonstrate that the proposed algorithms are much more efficient than the competing ones for computing the projections.

AB - We consider the problem of computing the Euclidean projection of a vector of length n onto a closed convex set including the ℓ1 and the specialized polyhedra employed in (Shalev-Shwartz & Singer, 2006). These problems have played building block roles in solving several ℓ1-norm based sparse learning problems. Existing methods have a worst-case time complexity of O(n log n). In this paper, we propose to cast both Euclidean projections as root finding problems associated with specific auxiliary functions, which can be solved in linear time via bisection. We further make use of the special structure of the auxiliary functions, and propose an improved bisection algorithm. Empirical studies demonstrate that the proposed algorithms are much more efficient than the competing ones for computing the projections.

UR - http://www.scopus.com/inward/record.url?scp=71149115443&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71149115443&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781605585161

SP - 657

EP - 664

BT - Proceedings of the 26th International Conference On Machine Learning, ICML 2009

ER -