The convergence analysis and specification of the Population-Based Incremental Learning algorithm

Helong LI; Sam KWONG; Yi HONG

doi:10.1016/j.neucom.2010.06.032

The convergence analysis and specification of the Population-Based Incremental Learning algorithm

Helong LI
, Sam KWONG
, Yi HONG

Research output: Journal Publications › Journal Article (refereed) › peer-review

6 Citations (Scopus)

Abstract

In this paper, we investigate the global convergence properties in probability of the Population-Based Incremental Learning (PBIL) algorithm when the initial configuration p(0) is fixed and the learning rate α is close to zero. The convergence in probability of PBIL is confirmed by the experimental results. This paper presents a meaningful discussion on how to establish a unified convergence theory of PBIL that is not affected by the population and the selected individuals. © 2011 Elsevier B.V.

Original language	English
Pages (from-to)	1868-1873
Journal	Neurocomputing
Volume	74
Issue number	11
DOIs	https://doi.org/10.1016/j.neucom.2010.06.032
Publication status	Published - May 2011
Externally published	Yes

Funding

This work is supported by City University Strategic Grant (7002441), the Fundamental Research Funds for the Central Universities, SCUT (2009ZM0081), NSFC(10826053, 60825306, U0735004) and GDSF(07118074).

Keywords

Convergence
Global optimum
Population-Based Incremental Learning (PBIL)

Access to Document

10.1016/j.neucom.2010.06.032

Cite this

@article{4e94c2b1b53949bfa6e56389cb7db590,

title = "The convergence analysis and specification of the Population-Based Incremental Learning algorithm",

abstract = "In this paper, we investigate the global convergence properties in probability of the Population-Based Incremental Learning (PBIL) algorithm when the initial configuration p(0) is fixed and the learning rate α is close to zero. The convergence in probability of PBIL is confirmed by the experimental results. This paper presents a meaningful discussion on how to establish a unified convergence theory of PBIL that is not affected by the population and the selected individuals. {\textcopyright} 2011 Elsevier B.V.",

keywords = "Convergence, Global optimum, Population-Based Incremental Learning (PBIL)",

author = "Helong LI and Sam KWONG and Yi HONG",

year = "2011",

month = may,

doi = "10.1016/j.neucom.2010.06.032",

language = "English",

volume = "74",

pages = "1868--1873",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier B.V.",

number = "11",

}

TY - JOUR

T1 - The convergence analysis and specification of the Population-Based Incremental Learning algorithm

AU - LI, Helong

AU - KWONG, Sam

AU - HONG, Yi

PY - 2011/5

Y1 - 2011/5

N2 - In this paper, we investigate the global convergence properties in probability of the Population-Based Incremental Learning (PBIL) algorithm when the initial configuration p(0) is fixed and the learning rate α is close to zero. The convergence in probability of PBIL is confirmed by the experimental results. This paper presents a meaningful discussion on how to establish a unified convergence theory of PBIL that is not affected by the population and the selected individuals. © 2011 Elsevier B.V.

AB - In this paper, we investigate the global convergence properties in probability of the Population-Based Incremental Learning (PBIL) algorithm when the initial configuration p(0) is fixed and the learning rate α is close to zero. The convergence in probability of PBIL is confirmed by the experimental results. This paper presents a meaningful discussion on how to establish a unified convergence theory of PBIL that is not affected by the population and the selected individuals. © 2011 Elsevier B.V.

KW - Convergence

KW - Global optimum

KW - Population-Based Incremental Learning (PBIL)

UR - https://www.scopus.com/pages/publications/79956057744

U2 - 10.1016/j.neucom.2010.06.032

DO - 10.1016/j.neucom.2010.06.032

M3 - Journal Article (refereed)

SN - 0925-2312

VL - 74

SP - 1868

EP - 1873

JO - Neurocomputing

JF - Neurocomputing

IS - 11

ER -

The convergence analysis and specification of the Population-Based Incremental Learning algorithm

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this