The future of experimental research

Bartz-Beielstein T., Preuss M.


Abstract
In the experimental analysis of metaheuristic methods, two issues are still not sufficiently treated. Firstly, the performance of algorithms depends on their parametrizations-and of the parametrizations of the problem instances. However, these dependencies can be seen as means for understanding an algorithm's behavior. Secondly, the nondeterminism of evolutionary and other metaheuristic methods renders result distributions, not numbers. Based on the experience of several tutorials on the matter, we provide a comprehensive, effective, and very efficient methodology for the design and experimental analysis of metaheuristics such as evolutionary algorithms. We rely on modern statistical techniques for tuning and understanding algorithms from an experimental perspective. Therefore, we make use of the sequential parameter optimization (SPO) method that has been successfully applied as a tuning procedure to numerous heuristics for practical and theoretical optimization problems. © 2010 Springer-Verlag Berlin Heidelberg.



Publication type
Chapter in Book

Peer reviewed
Yes

Publication status
Published

Year
2010

Book title
Experimental Methods for the Analysis of Optimization Algorithms

Editor
Bartz-Beielstein T., Chiarandini M., Paquete L., Preuss M.

Start page
17

End page
49

Pages range
17-49

Volume
null

Publisher
Springer Berlin Heidelberg

Language
English

ISBN
9783642025372

DOI

Full text

Affiliation
Fachhochschule Koln; Universitat Dortmund