Towards insightful algorithm selection for optimisation using meta-learning concepts
conference contribution
posted on 2008-01-01, 00:00authored byK Smith-Miles
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.
History
Event
IEEE World Congress on Computational Intelligence (2008 : Hong Kong)
Pagination
4118 - 4124
Publisher
IEEE
Location
Hong Kong
Place of publication
Piscataway, N.J.
Start date
2008-06-01
End date
2008-06-06
ISBN-13
9781424418213
Language
eng
Publication classification
E1 Full written paper - refereed
Copyright notice
2008, IEEE
Editor/Contributor(s)
J Wang
Title of proceedings
WCCI 2008 : IEEE World Congress on Computational Intelligence