On-Line Parameter Optimization Strategies for Metaheuristics
M. Affenzeller, L. Pöllabauer, G. K. Kronberger, E. Pitzer, S. Wagner, S. M. Winkler, A. Beham, M. Kofler - On-Line Parameter Optimization Strategies for Metaheuristics - 22nd European Modeling and Simulation Symposium EMSS 2010, Fes, Morocco, 2010, pp. 31-36
In this paper we describe different aspects of parameter tuning strategies for meta-heuristic algorithms. In contrast to many automated parameter adjustment methods in the field, special attention is given to parameter tuning strategies which are able to be applied during the run of a meta-heuristics. The basic idea we are using for this approach steams from self adaptive evolution strategies and this paper discusses different adaptations to this idea in order to find out, to which extent this concept can be transformed to other meta-heuristics.