Published on Thu Apr 30 2015

Average Convergence Rate of Evolutionary Algorithms

Jun He, Guangming Lin

In evolutionary optimization, it is important to understand how fast evolutionary algorithms converge to the optimum per generation. This paper proposes a new measure of the convergence rate, called average convergence rate.

0
0
0
Abstract

In evolutionary optimization, it is important to understand how fast evolutionary algorithms converge to the optimum per generation, or their convergence rate. This paper proposes a new measure of the convergence rate, called average convergence rate. It is a normalised geometric mean of the reduction ratio of the fitness difference per generation. The calculation of the average convergence rate is very simple and it is applicable for most evolutionary algorithms on both continuous and discrete optimization. A theoretical study of the average convergence rate is conducted for discrete optimization. Lower bounds on the average convergence rate are derived. The limit of the average convergence rate is analysed and then the asymptotic average convergence rate is proposed.

Sat Oct 27 2018
Neural Networks
Average Convergence Rate of Evolutionary Algorithms II: Continuous Optimization
A good convergence metric must satisfy two requirements: feasible in calculation and rigorous in analysis. The average convergence rate is proposed as a new measurement for evaluating the convergence speed of evolutionary algorithms.
0
0
0
Tue Jun 13 2017
Neural Networks
Investigating the Parameter Space of Evolutionary Algorithms
The practice of evolutionary algorithms involves the tuning of many parameters. Through an extensive series of experiments we show that parameter space tends to be rife with viable parameters.
0
0
0
Wed Nov 11 2015
Neural Networks
An Analytic Expression of Relative Approximation Error for a Class of Evolutionary Algorithms
An important question in evolutionary computation is how good solutions evolutionary algorithms can produce. This paper aims to provide an analyticanalysis of solution quality in terms of the relative approximation error.
0
0
0
Tue Aug 23 2011
Neural Networks
Novel Analysis of Population Scalability in Evolutionary Algorithms
Population scalability is the performance ratio between a benchmark EA and another EA using identical genetic operators but a larger population size. We demonstrate rigorously that for. identical global mutation, using a lager population size always increases the average rate of convergence to. the optimal set.
0
0
0
Mon Jun 03 2019
Neural Networks
2019 Evolutionary Algorithms Review
Evolutionary algorithm research and applications began over 50 years ago. New taxonomy of evolutionary algorithms looks at five main areas. These include the ability to manage the control of the environment with limiters. The ability to understand input and output causality within a solution.
0
0
0
Sun Nov 22 2015
Neural Networks
Evolutionary algorithms
This manuscript contains an outline of lectures course "Evolutionary Algorithms" read by the author. The course covers Canonic Genetic Algorithm and other genetic algorithms. The text is in Russian.
0
0
0