Foundations of Genetic Algorithms 2001 (FOGA 6)

Recursive Conditional Schema Theorem, Convergence and Population Sizing in Genetic Algorithms

Riccardo Poli [e-mail]    School of Computer Science The University of Birmingham Birmingham, B15 2TT, UK

Abstract

In this paper we start by presenting two forms of schema theorem in which expectations are not present. These theorems allow one to predict with a known probability whether the number of instances of a schema at the next generation will be above a given threshold. Then we clarify that in the presence of stochasticity schema theorems should be interpreted as conditional statements and we use a conditional version of schema theorem backwards to predict the past from the future. Assuming that at least x instances of a schema are present ...