Sufficient Conditions for Coarse-Graining Evolutionary Dynamics

TL;DR

This paper introduces a simple, abstract framework for analyzing the dynamics of infinite population evolutionary algorithms, providing conditions under which their complex behavior can be approximated efficiently, especially for long genomes.

Contribution

It develops a novel, general framework that allows coarse-graining of evolutionary dynamics without assumptions on genome structure or variation methods.

Findings

Derived abstract conditions for coarse-graining evolutionary dynamics.

Established concrete criteria for approximating schema frequencies in long-genome populations.

Demonstrated computational feasibility of tracking low-order schema frequencies over generations.

Abstract

It is commonly assumed that the ability to track the frequencies of a set of schemata in the evolving population of an infinite population genetic algorithm (IPGA) under different fitness functions will advance efforts to obtain a theory of adaptation for the simple GA. Unfortunately, for IPGAs with long genomes and non-trivial fitness functions there do not currently exist theoretical results that allow such a study. We develop a simple framework for analyzing the dynamics of an infinite population evolutionary algorithm (IPEA). This framework derives its simplicity from its abstract nature. In particular we make no commitment to the data-structure of the genomes, the kind of variation performed, or the number of parents involved in a variation operation. We use this framework to derive abstract conditions under which the dynamics of an IPEA can be coarse-grained. We then use this result to derive concrete conditions under which it becomes computationally feasible to closely approximate the frequencies of a family of schemata of relatively low order over multiple generations, even when the bitstsrings in the evolving population of the IPGA are long.