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

Helong LI, Sam KWONG, Yi HONG

Research output: Journal PublicationsJournal 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 languageEnglish
Pages (from-to)1868-1873
JournalNeurocomputing
Volume74
Issue number11
DOIs
Publication statusPublished - May 2011
Externally publishedYes

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)

Fingerprint

Dive into the research topics of 'The convergence analysis and specification of the Population-Based Incremental Learning algorithm'. Together they form a unique fingerprint.

Cite this