Conditions for the convergence of evolutionary algorithms
作者： Jun He , Xinghuo Yu
DOI: 10.1016/S1383-7621(01)00018-2
关键词:
摘要: This paper presents a theoretical analysis of the convergence conditions for evolutionary algorithms. The necessary and sufficient conditions, algorithms to global optima are derived, which describe their limiting behaviors. Their relationships explored. Upper lower bounds rates given.
elsevier.com
sci-hub.se 参考文章(11)
José Carlos Príncipe, Thomas E. Davis, A Simulated Annealing Like Convergence Theory for the Simple Genetic Algorithm international conference on genetic algorithms. pp. 174- 181 ,(1991)
Raphaël Cerf, An Asymptotic Theory of Genetic Algorithms european conference on artificial evolution. pp. 37- 53 ,(1995)
Jun He, Lishan Kang, On the convergence rates of genetic algorithms Theoretical Computer Science. ,vol. 229, pp. 23- 39 ,(1999) , 10.1016/S0304-3975(99)00091-2
Hans-Georg Beyer, Toward a theory of evolution strategies: On the benefits of sex---the (μ/μ, λ) theory Evolutionary Computation. ,vol. 3, pp. 81- 111 ,(1995) , 10.1162/EVCO.1995.3.1.81
Günter Rudolph, Finite Markov Chain Results in Evolutionary Computation: A Tour d'Horizon Fundamenta Informaticae. ,vol. 35, pp. 67- 89 ,(1998) , 10.3233/FI-1998-35123405
G. Rudolph, Convergence analysis of canonical genetic algorithms IEEE Transactions on Neural Networks. ,vol. 5, pp. 96- 101 ,(1994) , 10.1109/72.265964
A. E. Eiben, E. H. L. Aarts, K. M. Van Hee, Global Convergence of Genetic Algorithms: A Markov Chain Analysis parallel problem solving from nature. pp. 4- 12 ,(1990) , 10.1007/BFB0029725
G. Rudolph, Convergence of non-elitist strategies world congress on computational intelligence. pp. 63- 66 ,(1994) , 10.1109/ICEC.1994.350041
J. Suzuki, A Markov chain analysis on simple genetic algorithms systems man and cybernetics. ,vol. 25, pp. 655- 659 ,(1995) , 10.1109/21.370197
A.E. Eiben, G. Rudolph, Theory of evolutionary algorithms: a bird's eye view Theoretical Computer Science. ,vol. 229, pp. 3- 9 ,(1999) , 10.1016/S0304-3975(99)00089-4