Rigorous analyses of fitness-proportional selection for optimizing linear functions
Date
2008
Authors
Happ, E.
Johannsen, D.
Klein, C.
Neumann, F.
Editors
Ryan, C.
Keijzer, M.
Keijzer, M.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
GECCO '08: Proceedings of the 10th annual conference on Genetic and evolutionary computation / M. Keijzer (ed.), pp.953-960
Statement of Responsibility
Edda Happ, Daniel Johannsen, Christian Klein, Frank Neumann
Conference Name
Genetic and Evolutionary Computation Conference (10th : 2008 : Atlanta, Georgia)
Abstract
Rigorous runtime analyses of evolutionary algorithms (EAs) mainly investigate algorithms that use elitist selection methods. Two algorithms commonly studied are Randomized Local Search (RLS) and the (1+1) EA and it is well known that both optimize any linear pseudo-Boolean function on n bits within an expected number of O(n log n) fitness evaluations. In this paper, we analyze variants of these algorithms that use fitness proportional selection. A well-known method in analyzing the local changes in the solutions of RLS is a reduction to the gambler's ruin problem. We extend this method in order to analyze the global changes imposed by the (1+1) EA. By applying this new technique we show that with high probability using fitness proportional selection leads to an exponential optimization time for any linear pseudo-Boolean function with non-zero weights. Even worse, all solutions of the algorithms during an exponential number of fitness evaluations differ with high probability in linearly many bits from the optimal solution. Our theoretical studies are complemented by experimental investigations which confirm the asymptotic results on realistic input sizes.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright 2008 ACM