Level-based Analysis of Genetic Algorithms and other Search Processes
Abstract
Understanding how the time-complexity of evolutionary algorithms (EAs) depend on their parameter settings and characteristics of fitness landscapes is a fundamental problem in evolutionary computation. Most rigorous results were derived using a handful of key analytic techniques, including drift analysis. However, since few of these techniques apply effortlessly to population-based EAs, most time-complexity results concern simplified EAs, such as the (1+1) EA. This paper describes the level-based theorem, a new technique tailored to population-based processes. It applies to any non-elitist process where offspring are sampled independently from a distribution depending only on the current population. Given conditions on this distribution, our technique provides upper bounds on the expected time until the process reaches a target state. We demonstrate the technique on several pseudo-Boolean functions, the sorting problem, and approximation of optimal solutions in combinatorial optimisation. The conditions of the theorem are often straightforward to verify, even for Genetic Algorithms and Estimation of Distribution Algorithms which were considered highly non-trivial to analyse. Finally, we prove that the theorem is nearly optimal for the processes considered. Given the information the theorem requires about the process, a much tighter bound cannot be proved.
Cite
@article{arxiv.1407.7663,
title = {Level-based Analysis of Genetic Algorithms and other Search Processes},
author = {Dogan Corus and Duc-Cuong Dang and Anton V. Eremeev and Per Kristian Lehre},
journal= {arXiv preprint arXiv:1407.7663},
year = {2016}
}
Comments
This is a revised version of a paper published in the proceedings of PPSN 2014. The time-complexity bound is more precise. The proofs have been revised and simplified. More examples are added. Finally, we prove that the level-based theorem is close to optimal for the class of evolutionary processes it applies to