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 o spring 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 combina-torial optimisation. The conditions of the theorem are often straightfor-ward 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.
Footnotes
↵* Dogan Corus’ contributions to this paper was made while he was a PhD student at the University of Nottingham.
1 The first level can be A0 instead of A1 for some functions but that does not matter as far as we compute the sums correctly later on.