Bayesian inference in estimation of distribution algorithms

Marcus Gallagher; Ian Wood; Jonathan Keith; George Sofronov

doi:10.1109/CEC.2007.4424463

Bayesian inference in estimation of distribution algorithms

Marcus Gallagher^*, Ian Wood, Jonathan Keith, George Sofronov

^*Corresponding author for this work

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

14 Citations (Scopus)

151 Downloads (Pure)

Abstract

Metaheuristics such as Estimation of Distribution Algorithms and the Cross-Entropy method use probabilistic modelling and inference to generate candidate solutions in optimization problems. The model fitting task in this class of algorithms has largely been carried out to date based on maximum likelihood. An alternative approach that is prevalent in statistics and machine learning is to use Bayesian inference. In this paper, we provide a framework for the application of Bayesian inference techniques in probabilistic model-based optimization. Based on this framework, a simple continuous Bayesian Estimation of Distribution Algorithm is described. We evaluate and compare this algorithm experimentally with its maximum likelihood equivalent, UMDA_c ^G.

Original language	English
Title of host publication	2007 IEEE Congress on Evolutionary Computation, CEC 2007
Place of Publication	Piscataway, N.J
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	127-133
Number of pages	7
ISBN (Print)	1424413400, 9781424413409
DOIs	https://doi.org/10.1109/CEC.2007.4424463
Publication status	Published - 2007
Externally published	Yes
Event	2007 IEEE Congress on Evolutionary Computation, CEC 2007 - , Singapore Duration: 25 Sept 2007 → 28 Sept 2007

Other

Other	2007 IEEE Congress on Evolutionary Computation, CEC 2007
Country/Territory	Singapore
Period	25/09/07 → 28/09/07

Bibliographical note

Copyright 2007 IEEE. Reprinted from Evolutionary Computation, 2007, CEC 2007, IEEE Congress on : date 25-28 Sept. 2007. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of Macquarie Universityâ€™s products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

Access to Document

10.1109/CEC.2007.4424463

Publisher version (open access).pdfFinal published version, 302 KB

Cite this

@inproceedings{766721900fb24ba49ba457bcd43f4bab,

title = "Bayesian inference in estimation of distribution algorithms",

abstract = "Metaheuristics such as Estimation of Distribution Algorithms and the Cross-Entropy method use probabilistic modelling and inference to generate candidate solutions in optimization problems. The model fitting task in this class of algorithms has largely been carried out to date based on maximum likelihood. An alternative approach that is prevalent in statistics and machine learning is to use Bayesian inference. In this paper, we provide a framework for the application of Bayesian inference techniques in probabilistic model-based optimization. Based on this framework, a simple continuous Bayesian Estimation of Distribution Algorithm is described. We evaluate and compare this algorithm experimentally with its maximum likelihood equivalent, UMDAc G.",

author = "Marcus Gallagher and Ian Wood and Jonathan Keith and George Sofronov",

note = "Copyright 2007 IEEE. Reprinted from Evolutionary Computation, 2007, CEC 2007, IEEE Congress on : date 25-28 Sept. 2007. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of Macquarie University{\^a}€{\texttrademark}s products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.; 2007 IEEE Congress on Evolutionary Computation, CEC 2007 ; Conference date: 25-09-2007 Through 28-09-2007",

year = "2007",

doi = "10.1109/CEC.2007.4424463",

language = "English",

isbn = "1424413400",

pages = "127--133",

booktitle = "2007 IEEE Congress on Evolutionary Computation, CEC 2007",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Gallagher, M, Wood, I, Keith, J & Sofronov, G 2007, Bayesian inference in estimation of distribution algorithms. in 2007 IEEE Congress on Evolutionary Computation, CEC 2007., 4424463, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, N.J, pp. 127-133, 2007 IEEE Congress on Evolutionary Computation, CEC 2007, Singapore, 25/09/07. https://doi.org/10.1109/CEC.2007.4424463

Bayesian inference in estimation of distribution algorithms. / Gallagher, Marcus; Wood, Ian; Keith, Jonathan et al.
2007 IEEE Congress on Evolutionary Computation, CEC 2007. Piscataway, N.J: Institute of Electrical and Electronics Engineers (IEEE), 2007. p. 127-133 4424463.

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

TY - GEN

T1 - Bayesian inference in estimation of distribution algorithms

AU - Gallagher, Marcus

AU - Wood, Ian

AU - Keith, Jonathan

AU - Sofronov, George

N1 - Copyright 2007 IEEE. Reprinted from Evolutionary Computation, 2007, CEC 2007, IEEE Congress on : date 25-28 Sept. 2007. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of Macquarie Universityâ€™s products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

PY - 2007

Y1 - 2007

N2 - Metaheuristics such as Estimation of Distribution Algorithms and the Cross-Entropy method use probabilistic modelling and inference to generate candidate solutions in optimization problems. The model fitting task in this class of algorithms has largely been carried out to date based on maximum likelihood. An alternative approach that is prevalent in statistics and machine learning is to use Bayesian inference. In this paper, we provide a framework for the application of Bayesian inference techniques in probabilistic model-based optimization. Based on this framework, a simple continuous Bayesian Estimation of Distribution Algorithm is described. We evaluate and compare this algorithm experimentally with its maximum likelihood equivalent, UMDAc G.

AB - Metaheuristics such as Estimation of Distribution Algorithms and the Cross-Entropy method use probabilistic modelling and inference to generate candidate solutions in optimization problems. The model fitting task in this class of algorithms has largely been carried out to date based on maximum likelihood. An alternative approach that is prevalent in statistics and machine learning is to use Bayesian inference. In this paper, we provide a framework for the application of Bayesian inference techniques in probabilistic model-based optimization. Based on this framework, a simple continuous Bayesian Estimation of Distribution Algorithm is described. We evaluate and compare this algorithm experimentally with its maximum likelihood equivalent, UMDAc G.

UR - https://www.scopus.com/pages/publications/77952750332

U2 - 10.1109/CEC.2007.4424463

DO - 10.1109/CEC.2007.4424463

M3 - Conference proceeding contribution

AN - SCOPUS:77952750332

SN - 1424413400

SN - 9781424413409

SP - 127

EP - 133

BT - 2007 IEEE Congress on Evolutionary Computation, CEC 2007

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, N.J

T2 - 2007 IEEE Congress on Evolutionary Computation, CEC 2007

Y2 - 25 September 2007 through 28 September 2007

ER -

Bayesian inference in estimation of distribution algorithms

Abstract

Other

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this