Runtime analysis of competitive co-evolutionary algorithms for maximin optimisation of a bilinear function

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

87 Downloads (Pure)

Abstract

Co-evolutionary algorithms have a wide range of applications, such as in hardware design, evolution of strategies for board games, and patching software bugs. However, these algorithms are poorly understood and applications are often limited by pathological behaviour, such as loss of gradient, relative over-generalisation, and mediocre objective stasis. It is an open challenge to develop a theory that can predict when co-evolutionary algorithms find solutions efficiently and reliably.

This paper provides a first step in developing runtime analysis for population-based competitive co-evolutionary algorithms. We provide a mathematical framework for describing and reasoning about the performance of co-evolutionary processes. An example application of the framework shows a scenario where a simple co-evolutionary algorithm obtains a solution in polynomial expected time. Finally, we describe settings where the co-evolutionary algorithm needs exponential time with overwhelmingly high probability to obtain a solution.
Original languageEnglish
Title of host publicationGECCO '22
Subtitle of host publicationProceedings of the Genetic and Evolutionary Computation Conference
EditorsJonathan E. Fieldsend
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Pages1408–1416
Number of pages9
ISBN (Electronic)9781450392372
DOIs
Publication statusPublished - 8 Jul 2022
EventGECCO '22: Genetic and Evolutionary Computation Conference - Boston, United States
Duration: 9 Jul 202213 Jul 2022

Publication series

NameGECCO: Genetic and Evolutionary Computation Conference

Conference

ConferenceGECCO '22: Genetic and Evolutionary Computation Conference
Abbreviated titleGECCO 2022
Country/TerritoryUnited States
CityBoston
Period9/07/2213/07/22

Bibliographical note

Funding Information:
Lehre was supported by a Turing AI Fellowship (EPSRC grant ref EP/V025562/1).

Publisher Copyright:
© 2022 ACM.

Keywords

  • Co-evolution
  • Runtime Analysis

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Theoretical Computer Science

Fingerprint

Dive into the research topics of 'Runtime analysis of competitive co-evolutionary algorithms for maximin optimisation of a bilinear function'. Together they form a unique fingerprint.

Cite this