Abstract
Memetic evolutionary algorithms (MEAs) combine the global search of evolutionary learning methods and the fine-tune ability of local search methods so that they are orders of magnitude more accurate than traditional evolutionary algorithms in many problem domains. However, little work has been done on the mathematical model and convergence analysis of MEAs. In this paper, a theoretical model as well as the convergence analysis of a class of gradient-based MEAs is presented. The results of this paper are extensions of the research work on the abstract model and convergence analysis of general evolutionary algorithms. By modeling the local search of gradient methods as an abstract strong evolution operator, the theoretical framework for abstract memetic evolutionary algorithms is derived. Moreover, the global convergence theorems and the convergence rate estimations of gradient-based MEAs are also established.
Supported by the National Natural Science Foundation of China Under Grant 60303012, 60234030, Chinese Post-Doctor Science Foundation under Grant 200403500202, and A Project Supported by Scientific Research Fund of Hunan Provincial Education Department.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bäck, T.: Evolutionary Algorithms in Theory and Practice: Evolution Strategies, Evolutionary Programming, Genetic Algorithms. Oxford University Press, Oxford (1996)
Moscato, P., Norman, M.G.: A Memetic Approach for the Traveling Salesman Problem: Implementation of a Computational Ecology for Combinatorial Optimization on Message-Passing Systems. In: Valero, M., Onate, E., Jane, M., Larriba, J.L., Suarez, B. (eds.) Parallel Computing and Transputer Applications, pp. 177–186. IOS Press, Amsterdam (1992)
Steenbeek, A.G., Marchiori, E., Eiben, A.E.: Finding Balanced Graph Bi-partitions Using a Hybrid Genetic Algorithm. In: Proceedings of the IEEE International Conference on Evolutionary Computation ICEC 1998, pp. 90–95. IEEE Press, Piscataway (1998)
Merz, P., Freisleben, B.: Fitness Landscape Analysis and Memetic Algorithms for the Quadratic Assignment Problem. IEEE Transactions on Evolutionary Computation 4(4), 337–352 (2000)
Merz, P., Freisleben, B.: Fitness Landscapes, Memetic Algorithms, and Greedy Operators for Graph Bipartitioning. Evolutionary Computation 8(1), 61–91 (2000)
Francois, O.: Convergence in Simulated Evolution Algorithms. Complex Systems 10, 311–319 (1996)
Koehler, G.J.: A Proof of the Vose-Liepins Conjecture. Annals of Mathematics and Artificial Intelligence 10, 409–422 (1994)
Dawid, H.: A Markov Chain Analysis of Genetic Algorithms with a State Dependent Fitness Function. Complex Systems 8, 407–417 (1994)
Hart, W.E.: A Convergence Analysis of Unconstrained and Bound Constrained Evolutionary Pattern Search. Evolutionary Computation 9(1), 1–23 (2001)
Hart, W.E.: Evolutionary Pattern Search Algorithms for Unconstrained and Linearly Constrained Optimization. IEEE Trans. Evolutionary Computation 5(4), 388–397 (2001)
Leung, K.W., Duan, Q.H., Xu, Z.B., Wong, C.K.: A New Model of Simulated Evolutionary Computation—Convergence Analysis and Specifications. IEEE Trans. on Evolutionary Computation 5(1), 3–16 (2001)
Castillo, P.A., Merelo, J.J., Rivas, V., Romero, G., Prieto, A.: G-Prop: Global Optimization of Multilayer Perceptrons using GAs. Neurocomputing 35(1-4), 149–163 (2000)
Xu, X., He, H.G., Hu, D.W.: Evolutionary Adaptive-Critic Methods for Reinforcement Learning. In: Proc. of the IEEE Congress on Evolutionary Computation, pp. 1320–1325. IEEE Press, Los Alamitos (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xu, X., He, Hg. (2005). A Theoretical Model and Convergence Analysis of Memetic Evolutionary Algorithms. In: Wang, L., Chen, K., Ong, Y.S. (eds) Advances in Natural Computation. ICNC 2005. Lecture Notes in Computer Science, vol 3611. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11539117_142
Download citation
DOI: https://doi.org/10.1007/11539117_142
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28325-6
Online ISBN: 978-3-540-31858-3
eBook Packages: Computer ScienceComputer Science (R0)