Statistical Analysis of Evolution Strategy
Kunikazu Uesugi, Toshiharu Hatanaka, Katsuji Uosaki · Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications · 1997
Evolution strategy (ES), one of the evolutionary algorithms (EAs), is a probabilistic search and optimization method, modeling organic evolution process with recombination, mutation and selection. It has been shown empirically that this algorithm has potential for the global optimal search, but the analytical and systematic studies on it are few. This paper presents results of systematic statistical analysis of the effect of strategy parameters such as population size and step size in mutation in a simple ES. It will provide some guideline of choosing these parameters and future theoretical research.