Towards insightful algorithm selection for optimisation using meta-learning concepts

Kate Amanda Smith-Miles

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

68 Citations (Scopus)

Abstract

In this paper we propose a meta-learning inspired framework for analysing the performance of meta-heuristics for optimization problems, and developing insights into the relationships between search space characteristics of the problem instances and algorithm performance. Preliminary results based on several meta-heuristics for well-known instances of the Quadratic Assignment Problem are presented to illustrate the approach using both supervised and unsupervised learning methods.
Original languageEnglish
Title of host publication2008 IEEE World Congress on Computational Intelligence
EditorsDerong Liu
Place of PublicationHong Kong
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages4118 - 4124
Number of pages7
ISBN (Print)978-1-4244-1820-6
Publication statusPublished - 2008
Externally publishedYes
EventIEEE International Joint Conference on Neural Networks 2008 - Hong Kong Convention and Exhibition Centre, Hong Kong
Duration: 1 Jan 2008 → …

Conference

ConferenceIEEE International Joint Conference on Neural Networks 2008
Abbreviated titleIJCNN 2008
CityHong Kong
Period1/01/08 → …

Cite this

Smith-Miles, K. A. (2008). Towards insightful algorithm selection for optimisation using meta-learning concepts. In D. Liu (Ed.), 2008 IEEE World Congress on Computational Intelligence (pp. 4118 - 4124). IEEE, Institute of Electrical and Electronics Engineers.