Automatically assigned DDC number: 0051

Manually assigned DDC number: 00631

Title: Asymptotical Convergence Rates of Simple Evolutionary Algorithms under Factorizing Mutation Distributions

Author:

Subject: Gunter Rudolph Asymptotical Convergence Rates of Simple Evolutionary Algorithms under Factorizing Mutation Distributions

Description: . The standard choice for mutating an individual of an evolutionary algorithm with continuous variables is the normal distribution. It is shown that there is a broad class of alternative mutation distributions offering local convergence rates being asymptotical equal to the convergence rates achieved with normally distributed mutations. Such mutation distributions must be factorizing and the absolute fourth moments must be finite. Under these conditions an asymptotical theory of the convergence rates of simple evolutionary algorithms can be established for the entire class of distributions. 1 Introduction The standard choice to represent mutations in evolutionary models dealing with continuous quantities is the normal distribution. This choice is usually justified by the central limit theorem: Since mutations in nature are caused by a variety of physical and chemical influences that are not identifiable or measurable to a degree that allows for a deterministic model, these influences ...

Contributor: The Pennsylvania State University CiteSeer Archives

Publisher: unknown

Date: 1997-10-10

Pubyear: 1997

Format: ps

Identifier: http://citeseer.ist.psu.edu/140370.html

Source: http://ls11-www.informatik.uni-dortmund.de/people/rudolph/publications/Rud98.ps.gz

Language: en

Rights: unrestricted