Generalized Evolutionary Algorithm based on Tsallis Statistics

Department of Computer Science and Automation Indian Institute of Science, Bangalore 560012, India(Dated: February 1, 2008)Generalized evolutionary algorithm based on Tsallis canonical distribution is proposed. Thealgorithm uses Tsallis generalized canonical distribution to weigh the configurations for ‘selection’instead of Gibbs-Boltzmann distribution. Our simulation results show that for an appropriatechoice of non-extensive index that is offered by Tsallis statistics, evolutionary algorithms based onthis generalization outperform algorithms based on Gibbs-Boltzmann distribution.