Title :
Convergence of non-elitist strategies
Author_Institution :
Fachbereich Inf., Dortmund Univ., Germany
Abstract :
The paper offers sufficient conditions to prove global convergence of non-elitist evolutionary algorithms. If these conditions can be applied they yield bounds of the convergence rate as a by-product. This is demonstrated by an example that can be calculated exactly
Keywords :
convergence of numerical methods; genetic algorithms; search problems; EA; convergence rate; genetic algorithms; global convergence; martingale theory; non-elitist evolutionary algorithms; non-elitist strategies; nonelitist strategies; Convergence; Evolutionary computation; Genetic algorithms; Genetic mutations; Genetic programming; Optimization methods; Parallel processing; Random sequences; Random variables; Research initiatives;
Conference_Titel :
Evolutionary Computation, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the First IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1899-4
DOI :
10.1109/ICEC.1994.350041
