CEoptim: cross-entropy R package for optimization

Tim Benham; Qibin Duan; Dirk P. Kroese; Benoît Liquet

doi:10.18637/jss.v076.i08

CEoptim: cross-entropy R package for optimization

Tim Benham, Qibin Duan, Dirk P. Kroese, Benoît Liquet

Research output: Contribution to journal › Article › peer-review

12 Citations (Scopus)

56 Downloads (Pure)

Abstract

The cross-entropy (CE) method is a simple and versatile technique for optimization, based on Kullback-Leibler (or cross-entropy) minimization. The method can be applied to a wide range of optimization tasks, including continuous, discrete, mixed and constrained optimization problems. The new package CEoptim provides the R implementation of the CE method for optimization. We describe the general CE methodology for optimization and well as some useful modifications. The usage and efficacy of CEoptim is demonstrated through a variety of optimization examples, including model fitting, combinatorial optimization, and maximum likelihood estimation.

Original language	English
Pages (from-to)	1-29
Number of pages	29
Journal	Journal of Statistical Software
Volume	76
Issue number	8
DOIs	https://doi.org/10.18637/jss.v076.i08
Publication status	Published - Feb 2017
Externally published	Yes

Bibliographical note

Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

constrained optimization
continuous optimization
cross-entropy
discrete optimization
Kullback-Leibler divergence
lasso
maximum likelihood
R
regression

Access to Document

10.18637/jss.v076.i08Licence: CC BY

Publisher version (open access)Final published version, 738 KBLicence: CC BY

https://arxiv.org/abs/1503.01842

Cite this

@article{f4c449881fc348c2a4497a5fe2c144b0,

title = "CEoptim: cross-entropy R package for optimization",

abstract = "The cross-entropy (CE) method is a simple and versatile technique for optimization, based on Kullback-Leibler (or cross-entropy) minimization. The method can be applied to a wide range of optimization tasks, including continuous, discrete, mixed and constrained optimization problems. The new package CEoptim provides the R implementation of the CE method for optimization. We describe the general CE methodology for optimization and well as some useful modifications. The usage and efficacy of CEoptim is demonstrated through a variety of optimization examples, including model fitting, combinatorial optimization, and maximum likelihood estimation.",

keywords = "constrained optimization, continuous optimization, cross-entropy, discrete optimization, Kullback-Leibler divergence, lasso, maximum likelihood, R, regression",

author = "Tim Benham and Qibin Duan and Kroese, \{Dirk P.\} and Beno{\^i}t Liquet",

note = "Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",

year = "2017",

month = feb,

doi = "10.18637/jss.v076.i08",

language = "English",

volume = "76",

pages = "1--29",

journal = "Journal of Statistical Software",

issn = "1548-7660",

publisher = "University of California at Los Angeles",

number = "8",

}

TY - JOUR

T1 - CEoptim

T2 - cross-entropy R package for optimization

AU - Benham, Tim

AU - Duan, Qibin

AU - Kroese, Dirk P.

AU - Liquet, Benoît

N1 - Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2017/2

Y1 - 2017/2

N2 - The cross-entropy (CE) method is a simple and versatile technique for optimization, based on Kullback-Leibler (or cross-entropy) minimization. The method can be applied to a wide range of optimization tasks, including continuous, discrete, mixed and constrained optimization problems. The new package CEoptim provides the R implementation of the CE method for optimization. We describe the general CE methodology for optimization and well as some useful modifications. The usage and efficacy of CEoptim is demonstrated through a variety of optimization examples, including model fitting, combinatorial optimization, and maximum likelihood estimation.

AB - The cross-entropy (CE) method is a simple and versatile technique for optimization, based on Kullback-Leibler (or cross-entropy) minimization. The method can be applied to a wide range of optimization tasks, including continuous, discrete, mixed and constrained optimization problems. The new package CEoptim provides the R implementation of the CE method for optimization. We describe the general CE methodology for optimization and well as some useful modifications. The usage and efficacy of CEoptim is demonstrated through a variety of optimization examples, including model fitting, combinatorial optimization, and maximum likelihood estimation.

KW - constrained optimization

KW - continuous optimization

KW - cross-entropy

KW - discrete optimization

KW - Kullback-Leibler divergence

KW - lasso

KW - maximum likelihood

KW - R

KW - regression

UR - https://www.scopus.com/pages/publications/85016071171

UR - http://purl.org/au-research/grants/arc/CE140100049

U2 - 10.18637/jss.v076.i08

DO - 10.18637/jss.v076.i08

M3 - Article

SN - 1548-7660

VL - 76

SP - 1

EP - 29

JO - Journal of Statistical Software

JF - Journal of Statistical Software

IS - 8

ER -

CEoptim: cross-entropy R package for optimization

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this