Analysing Equilibrium States for Population Diversity


Loading...

Date

2024-07

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Population diversity is crucial in evolutionary algorithms as it helps with global exploration and facilitates the use of crossover. Despite many runtime analyses showing advantages of population diversity, we have no clear picture of how diversity evolves over time. We study how the population diversity of (μ+1) algorithms, measured by the sum of pairwise Hamming distances, evolves in a fitness-neutral environment. We give an exact formula for the drift of population diversity and show that it is driven towards an equilibrium state. Moreover, we bound the expected time for getting close to the equilibrium state. We find that these dynamics, including the location of the equilibrium, are unaffected by surprisingly many algorithmic choices. All unbiased mutation operators with the same expected number of bit flips have the same effect on the expected diversity. Many crossover operators have no effect at all, including all binary unbiased, respectful operators. We review crossover operators from the literature and identify crossovers that are neutral towards the evolution of diversity and crossovers that are not.

Publication status

published

Editor

Book title

Journal / series

Volume

86 (7)

Pages / Article No.

1 - 35

Publisher

Springer

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Evolutionary algorithms; Runtime analysis; Diversity; Population dynamics

Organisational unit

08738 - Lengler, Johannes (Tit.-Prof.) / Lengler, Johannes (Tit.-Prof.) check_circle

Notes

Funding

Related publications and datasets

Is new version of: