Efficient euclidean projections in linear time

Jun Liu, Jieping Ye

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

5 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 ball and the specialized polyhedra employed in (Shalev-Shwartz & Singer, 2006). These problems have played building block roles in solving several l 1- 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 publicationACM International Conference Proceeding Series
Volume382
DOIs
StatePublished - 2009
Event26th Annual International Conference on Machine Learning, ICML'09 - Montreal, QC, Canada
Duration: Jun 14 2009Jun 18 2009

Other

Other26th Annual International Conference on Machine Learning, ICML'09
CountryCanada
CityMontreal, QC
Period6/14/096/18/09

ASJC Scopus subject areas

  • Human-Computer Interaction

Cite this

Liu, J., & Ye, J. (2009). Efficient euclidean projections in linear time. In ACM International Conference Proceeding Series (Vol. 382). [82] https://doi.org/10.1145/1553374.1553459

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

ACM International Conference Proceeding Series. Vol. 382 2009. 82.

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

Liu, J & Ye, J 2009, Efficient euclidean projections in linear time. in ACM International Conference Proceeding Series. vol. 382, 82, 26th Annual International Conference on Machine Learning, ICML'09, Montreal, QC, Canada, 6/14/09. https://doi.org/10.1145/1553374.1553459
Liu J, Ye J. Efficient euclidean projections in linear time. In ACM International Conference Proceeding Series. Vol. 382. 2009. 82 https://doi.org/10.1145/1553374.1553459
Liu, Jun ; Ye, Jieping. / Efficient euclidean projections in linear time. ACM International Conference Proceeding Series. Vol. 382 2009.
@inproceedings{4a5b2135497f4ee992e13697e1eebeb1,
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 ball and the specialized polyhedra employed in (Shalev-Shwartz & Singer, 2006). These problems have played building block roles in solving several l 1- 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",
doi = "10.1145/1553374.1553459",
language = "English (US)",
isbn = "9781605585161",
volume = "382",
booktitle = "ACM International Conference Proceeding Series",

}

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 ball and the specialized polyhedra employed in (Shalev-Shwartz & Singer, 2006). These problems have played building block roles in solving several l 1- 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 ball and the specialized polyhedra employed in (Shalev-Shwartz & Singer, 2006). These problems have played building block roles in solving several l 1- 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=70049101203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70049101203&partnerID=8YFLogxK

U2 - 10.1145/1553374.1553459

DO - 10.1145/1553374.1553459

M3 - Conference contribution

AN - SCOPUS:70049101203

SN - 9781605585161

VL - 382

BT - ACM International Conference Proceeding Series

ER -