The Gene Expression Messy Genetic Algorithm

This paper introduces the gene expression messy genetic algorithm (GEMGA)|a new generation of messy GAs that directly search for relations among the members of the search space. The GEMGA is an O((k (` 2 + k)) sample complexity algorithm for the class of order-k deline-able problems 6] (problems that can be solved by considering no higher than order-k relations). The GEMGA is designed based on an alternate perspective of natural evolution proposed by the SEARCH framework 6] that emphasizes the role of gene expression. The GEMGA uses the transcription operator to search for relations. This paper also presents the test results of the GEMGA for large multimodal order-k delineable problems.