DeepAI AI Chat
Log In Sign Up

A Revisit of Infinite Population Models for Evolutionary Algorithms on Continuous Optimization Problems

by   Bo Song, et al.
The University of Hong Kong

Infinite population models are important tools for studying population dynamics of evolutionary algorithms. They describe how the distributions of populations change between consecutive generations. In general, infinite population models are derived from Markov chains by exploiting symmetries between individuals in the population and analyzing the limit as the population size goes to infinity. In this paper, we study the theoretical foundations of infinite population models of evolutionary algorithms on continuous optimization problems. First, we show that the convergence proofs in a widely cited study were in fact problematic and incomplete. We further show that the modeling assumption of exchangeability of individuals cannot yield the transition equation. Then, in order to analyze infinite population models, we build an analytical framework based on convergence in distribution of random elements which take values in the metric space of infinite sequences. The framework is concise and mathematically rigorous. It also provides an infrastructure for studying the convergence of the stacking of operators and of iterating the algorithm which previous studies failed to address. Finally, we use the framework to prove the convergence of infinite population models for the mutation operator and the k-ary recombination operator. We show that these operators can provide accurate predictions for real population dynamics as the population size goes to infinity, provided that the initial population is identically and independently distributed.


page 1

page 2

page 3

page 4


Convergence Properties of Two (μ + λ) Evolutionary Algorithms On OneMax and Royal Roads Test Functions

We present a number of bounds on convergence time for two elitist popula...

Theoretical Perspective of Convergence Complexity of Evolutionary Algorithms Adopting Optimal Mixing

The optimal mixing evolutionary algorithms (OMEAs) have recently drawn m...

CIXL2: A Crossover Operator for Evolutionary Algorithms Based on Population Features

In this paper we propose a crossover operator for evolutionary algorithm...

Evolutionary Optimization in an Algorithmic Setting

Evolutionary processes proved very useful for solving optimization probl...

Novel Analysis of Population Scalability in Evolutionary Algorithms

Population-based evolutionary algorithms (EAs) have been widely applied ...

Convergence of a Recombination-Based Elitist Evolutionary Algorithm on the Royal Roads Test Function

We present an analysis of the performance of an elitist Evolutionary alg...

Average Convergence Rate of Evolutionary Algorithms II: Continuous Optimization

A good convergence metric must satisfy two requirements: feasible in cal...