Abstract
We present a self-contained theoretical framework for a scaled genetic algorithm over the alphabet {0,1} which converges asymptotically to global optima as anticipated by Davis and Principe in analogy to the simulated annealing algorithm. The algorithm employs multiple-bit mutation, single-cut-point crossover and power-law scaled proportional fitness selection based upon an arbitrary fitness function. In order to achieve asymptotic convergence to global optima, the mutation and crossover rates have to be annealed to zero in proper fashion, and power-law scaling is used with logarithmic growth in the exponent. Our analysis shows that a large population size allows for a particularly slow annealing schedule for crossover. For the foremost described setting, a detailed listing of theoretical aspects is presented including prerequisites on inhomogeneous Markov chains. In particular, we focus on: (i) The drive towards uniform populations in a genetic algorithm. (ii) Weak and strong ergodicity of the inhomogeneous Markov chain describing the probabilistic model for the scaled algorithm. (iii) Convergence to globally optimal solutions. We discuss various generalizations and extensions of the core framework presented in this exposition such as larger alphabets or other versions of the mutation-crossover operator, in particular, the Vose-Liepins version of mutation-crossover. This refers to recent work by the author in [Theoretical Computer Science 259 (2001), 1–61] and [Technical Report 2002-2-002, Aizu University] where similar types of algorithms are considered over an arbitrary-size alphabet and convergence for arbitrary fitness function under more general conditions is shown. Finally, we present an outlook on further developments of the theory.
Chapter PDF
References
Aarts, E. H. L. and van Laarhoven, P. J. M. (1989). Simulated Annealing: An Introduction. Statistica Neerlandica, 43:31–52.
Agapie, A. (2001). Theoretical analysis of mutation-adaptive evolutionary algorithms. Evolutionary Computation, 9:127–146.
Anily, S. and Federgruen, A. (1987). Ergodicity in Parametric Non-Stationary Markov Chains: An Application to Simulated Annealing Methods. Operations Research, 35:867–874.
Aytug, H. and Koehler, G. J. (1996). Stopping Criteria for Finite Length Genetic Algorithms. INFORMS Journal on Computing, 8:183–191.
Azencott, R., editor (1992). Simulated Annealing — Parallelization Techniques. John Wiley & Sons Publishers.
Baker, J. E. (1987). Reducing Bias and Inefficiency in the Selection Algorithm. In Grefenstette, J. J., editor, Genetic Algorithms and Their Applications: Proceedings of the Second International Conference on Genetic Algorithms. Lawrence Erlbaum Publishers.
Banzhaf, W., Francone, F. D., and Nordin, P. (1996). The Effect of Extensive Use of the Mutation Operator on Generalization in Genetic Programming using Sparse Data Sets. In Ebeling, W., Rechenberg, I., Schwefel, H. P., and Voigt, H. M., editors, 4th International. Conference. on Parallel Problem Solving from Nature (PPSN96), pages 300–309. Springer Verlag.
Beyer, H.-G., Schwefel, H.-P., and Wegener, I. (2002). How to analyse evolutionary algorithms. Theoretical Computer Science, 287:101–130.
Binder, K. (1978). Monte Carlo methods in Statistical Physics. Springer Verlag.
Bremermann, H. J., Rogson, J., and Salaff, S. (1966). Global Properties of Evolution Processes. In Pattee, H. H., Edelsack, E., Fein, L., and Callahan, A., editors, Natural Automata and Useful Simulations, pages 3–42. Spartan Books, Washington DC.
Catoni, O. (1990). Large Deviations for Annealing. PhD thesis, Université Paris XI.
Catoni, O. (1991a). Applications of Sharp Large Deviations Estimates to Optimal Cooling Schedules. Annales de ľInstitute Henri Poincaré. Probabilités ét Statistique, 27:493–518.
Catoni, O. (1991b). Sharp Large Deviations Estimates for Simulated Annealing Algorithms. Annales de ľInstitute Henri Poincaré Probabilités ét Statistique, 27:291–383.
Catoni, O. (1992). Rough Large Deviations Estimates for Simulated Annealing — Application to Exponential Schedules. The Annals of Probability, 20:1109–1146.
Cerf, R. (1996). An Asymptotic Theory for Genetic Algorithms. In Alliot, J. M., Lutton, E., Ronald, E., Schoenauer, M., and Snyers, D., editors, Artificial Evolution. European Conference AE 95. Brest, France, September 4–6, 1995. Selected Papers, volume 1063 of Lecture Notes in Computer Science, pages 37–53. Springer Verlag.
Cerf, R. (1998). Asymptotic Convergence of Genetic Algorithms. Advances in Applied Probability, 30:521–550.
Chung, K. L. (1974). A Course in Probability Theory. Academic Press Publishers. Second edition.
Davis, T. (1991). Toward an Extrapolation of the Simulated Annealing Convergence Theory onto the Simple Genetic Algorithm. PhD thesis, University of Florida.
Davis, T. E. and Principe, J. C. (1991). A Simulated Annealing-like Convergence Theory for the Simple Genetic Algorithm. In Belew, R. K. and Booker, L. B., editors, Proceedings of the Fourth International Conference on Genetic Algorithms’ 91, pages 174–181. Morgan Kaufmann Publishers.
Davis, T. E. and Principe, J. C. (1993). A Markov Chain Framework for the Simple Genetic Algorithm. Evolutionary Computation, 1:269–288.
Droste, S., Jansen, T., Tinnefeld, K., and Wegener, I. (2003). A new framework for the valuation of algorithms for black-box optimization. In De Jong, K, Poli, R., and Rowe, J., editors, Foundations of Genetic Algorithms 7, pages 197–214. Morgan Kaufmann Publishers.
Droste, S., Jansen, T., and Wegener, I. (2002). On the Analysis of the (1 + 1) Evolutionary Algorithm. Theoretical Computer Science, 276:51–81.
Feller, W. (1968). An Introduction to Probability Theory and Its Applications. Volume 1. John Wiley & Sons Publishers. (third edition).
Feller, W. (1971). An Introduction to Probability Theory and Its Applications. Volume 2. John Wiley & Sons Publishers. (second edition).
Fogel, D. B. (1994). Asymptotic Convergence Properties of Genetic Algorithms and Evolutionary Programming: Analysis and Experiments. Cybernetics and Systems, 25:389–407.
Goldberg, D. E. Genetic Algorithms Tutorial. Genetic Programming Conference, Stanford University, (July 13, 1997).
Goldberg, D. E. (1989). Genetic Algorithms, in Search, Optimization & Machine Learning. Addison-Wesley Publishers.
Goldberg, D. E. (1990). A Note on Boltzmann Tournament Selection for Genetic Algorithms and Population Oriented Simulated Annealing. Complex Systems, 4:445–460.
Goldberg, D. E. and Deb, K. (1991). A Comparative Analysis of Selection Schemes used in Genetic Algorithms. In Rawlins, G. J. E., editor, Foundations of Genetic Algorithms, pages 69–93. Morgan Kaufmann Publishers.
Greenwood, G. W. and Zhu, Q. J. (2001). Convergence in Evolutionary Programs with Self-Adaptation. Evolutionary Computation, 9:147–157.
Greub, W. (1975). Linear Algebra. Springer-Verlag.
Griffiths, R. C. and Taveré, S. (1997). Computational Methods for the Coalescent. In Donnelly, P. and Taveré, S., editors, Progress in Population Genetics and Human Evolution, volume 87 of IMA Volumes in Mathematics and its Applications, pages 165–182. Springer Verlag.
Hajek, B. (1988). Cooling Schedules for Optimal Annealing. Mathematics of Operations Research, 13:345–351.
He, J. and Kang, L. (1999). On the Convergence Rates of Genetic Algorithms. Theoretical Computer Science, 229:23–39.
Holland, J. H. (1975). Adaptation in Natural and Artificial Systems. University of Michigan Press. Extended new edition. MIT Press (1992).
Isaacson, D. L. and Madsen, R. W. (1961). Markov Chains: Theory and Applications. Prentice-Hall Publishers.
Jansen, T. and Wegener, I. (2001). Real royal road functions — where crossover provably is essential. In Spector, L. and Goodman, E. D., editors, GECCO 2001, Proceedings of the Genetic and Evolutionary Computation Conference, pages 375–382. Morgan Kaufmann Publisher.
Knuth, D. E. (1997a). The Art of Computer Programming. Volume 3: Sorting and Searching. Addison-Wesley Publishers, Second Edition edition.
Knuth, D. E. (1997b). The Art of Computer Programming. Volume 1: Fundamental Algorithms. Addison-Wesley Publishers, Third Edition edition.
Knuth, D. E. (1997c). The Art of Computer Programming. Volume 2: Seminumerical Algorithms. Addison-Wesley Publishers, Third Edition edition.
Koehler, G. J. (1994). A Proof of the Vose-Liepins Conjecture. Annals of Mathematics and Artificial Intelligence, 10:408–422.
Kushner, H. J. (1987). Asymptotic Global Behavior for Stochastic Approximation and Diffusions with Slowly Decreasing Noise Effects: Global Minimization via Monte Carlo. SIAM Journal of Applied Mathematics, 47:169–185.
Landau, S. D. and Lifschitz, E. M. (1975). Lehrbuch der thoeretischen Physik V. Statistische Physik. Berlin: kademie Verlag.
Lang, S. (1968). Analysis I. Addison-Wesley Publishers.
Lang, S. (1970). Linear Algebra. Addison-Wesley Publishers, 2nd edition.
Leung, Y., Chen, Z.-P., Xu, Z.-B., and Leung, K.-S. (1998). Convergence Rate for Non-Binary Genetic Algorithms with Different Crossover Operators. The Chinese University of Hong Kong. (Preprint).
Lozano, J. A., Larrañaga, P., Graña, M., and Albizuri, F. X. (1999). Genetic Algorithms: bridging the Convergence Gap. Theoretical Computer Science, 229:23–39.
Lux, T. and Schornstein, S. (2002). Genetic learning as an Explanation of Stylized Facts of Foreign Exchange Markets. Manuscript, Universität Kiel, London School of Economics. pdf-file, www.bwl.uni-kiel.de/vwlinstitute/gwrp/ publications/publications.htm.
Mahfoud, S. W. (1993). Finite Markov Chain Models of an Alternative Selection Strategy for Genetic Algorithms. Complex Systems, 7:155–170.
Mahfoud, S. W. and Goldberg, D. E. (1992). A Genetic Algorithm for Parallel Simulated Annealing. In Männer, R. and Manderick, B., editors, Parallel Problem Solving from Nature, 2, pages 301–310. Elsevier Publishers.
Mahfoud, S. W. and Goldberg, D. E. (1995). Parallel Recombinative Simulated Annealing: a Genetic Algorithm. Parallel Computing, 21:1–28.
Márkus, A., Renner, G., and Vanza, J. (1997). Spline Interpolation with Genetic Algorithms. In Kunii, T. L., Falcidieno, B., Savchenko, V. V., and Pasko, A., editors, Proceedings of the International Conference on Shape Modeling, 1997, March 3–6, The University of Aizu, Aizu-Wakamatsu, Japan, pages 47–54. IEEE Computer Society Press.
Michalewicz, Z. (1994). Genetic Algorithms + Data Structures = Evolution Programs. Springer Verlag, 2nd edition.
Mitchell, M. (1996). An Introduction to Genetic Algorithms. MIT Press.
Mühlenbein, H. (1997). Genetic Algorithms. In Aarts, E. and Lenstra, L., editors, Local Search in Combinatorial Optimization, pages 131–171. John Wiley & Sons Publishers
Nix, A. E. and Vose, M. D. (1992). Modeling Genetic Algorithms with Markov Chains. Annals of Mathematics and Artificial Intelligence, 5:79–88.
Nomura, T. and Shimohara, K. (2001). An Analysis of Two-Parent Recombinations for Real-Valued Chromosomes in an Infinite Population. Evolutionary Computation, 9:283–308.
Poli, R. and Langdon, M. (1998). Schema Theory for Genetic Programming with One-Point Crossover and Point Mutation. Evolutionary Computation, 6(3):231–252.
Poli, R. (2001). Exact Schema Theory for Genetic Programming and Variable-Length Genetic Algorithms with One-Point Crossover. Genetic Programming and Evolvable Machines, 2:123–163.
Rudin, W. (1973). Functional Analysis. McGraw-Hill Publishers.
Rudolph, G. (1994). Convergence Analysis of Canonical Genetic Algorithms. IEEE Transactions on Neural Networks, 5:96–101.
Rudolph, G. (1997). Convergence Properties of Evolutionary Algorithms. Hamburg: Verlag Dr. Kovac.
Savchenko, V. and Schmitt, L. M. (2001). Reconstructing occlusal surfaces of teeth using a genetic algorithm with simulated annealing type selection. In Anderson, D. C. and Lee, K., editors, Proceedings of the Sixth ACM Symposium on Solid Modeling and Applications, pages 39–46. ACM Press.
Schaefer, H. H. (1974). Banach Lattices and Positive Operators, volume 215 of Die Grundlehren der mathematischen Wissenschaften in Einzeldarstellungen. Springer-Verlag.
Schmitt, L. M. (2001). Theory of Genetic Algorithms. Theoretical Computer Science, 259:1–61.
Schmitt, L. M. (2002). Theory of Genetic Algorithms II.–Convergence to optima for arbitrary fitness function. Technical Report 2002-2-002, The University of Aizu. (Submitted for journal publication).
Schmitt, L. M. and Kondoh, T. (2000). Optimization of Mass Distribution in Articulated Figures with Genetic Algorithms. In Hamza, M. H., editor, Proceedings of the 1ASTED International Conference “Applied Simulation and Modelling”, pages 191–197. IASTED/ACTA Press.
Schmitt, L. M. and Nehaniv, C. L. (1999). The Linear Geometry of Genetic Operators with Applications to the Analysis of Genetic Drift and Genetic Algorithms using Tournament Selection. In Nehaniv, C. L., editor, Mathematical and Computational Biology: Computational Morphogenesis, Hierarchical Complexity, and Digital Evolution, An International Workshop, 1997, October 21–25, The University of Aizu, Aizu-Wakamatsu, Japan, volume 26 of Lectures on Mathematics in the Life Sciences Series, pages 147–166. American Mathematical Society.
Schmitt, L. M., Nehaniv, C. L., and Fujii, R. H. (1998). Linear Analysis of Genetic Algorithms. Theoretical Computer Science, 200:101–134.
Seneta, E. (1981). Non-negative Matrices and Markov Chains. Springer Series in Statistics. Springer Verlag.
Suzuki, J. (1997). A Further Result on the Markov Chain Model of Genetic Algorithms and Its Application to a Simulated Annealing-like Strategy. In Belew, R. K. and Vose, M. D., editors, Foundations of Genetic Algorithms 4, pages 53–72. Morgan Kaufmann Publishers.
Suzuki, J. (1998). A Further Result on the Markov Chain Model of Genetic Algorithms and Its Application to a Simulated Annealing-like Strategy. IEEE Trans. on Systems, Man, and Cybernetics — Part B, 28:95–102.
van Nimwegen, E., Crutchfield, J. P., and Mitchell, M. (1999). Statistical Dynamics of the Royal Road Genetic Algorithm. Theoretical Computer Science, 229:41–102
Vose, M. D. and Wright, A. H. (1998a). The Simple Genetic Algorithm and the Walsh Transform: Part I, Theory. Evolutionary Computation, 6:253–273.
Vose, M. D. and Wright, A. H. (1998b). The Simple Genetic Algorithm and the Walsh Transform: Part II, The Inverse. Evolutionary Computation, 6:275–289.
Vose, M. D. (1999a). Random Heuristic Search. Theoretical Computer Science, 229:103–142.
Vose, M. D. (1999b). The Simple Genetic Algorithm: Foundations and Theory. MIT Press.
Vose, M. D. and Liepins, G. E. (1991). Punctuated Equilibria in Genetic Search. Complex Systems, 5:31–44.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Additional information
This work is dedicated to Joanne Watari and Makoto Yoshida in Aizu-Wakamatsu.
Rights and permissions
Copyright information
© 2004 Kluwer Academic Publishers
About this chapter
Cite this chapter
Schmitt, L.M. (2004). Asymptotic Convergence of Scaled Genetic Algorithms to Global Optima. In: Menon, A. (eds) Frontiers of Evolutionary Computation. Genetic Algorithms and Evolutionary Computation, vol 11. Springer, Boston, MA. https://doi.org/10.1007/1-4020-7782-3_8
Download citation
DOI: https://doi.org/10.1007/1-4020-7782-3_8
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4020-7524-7
Online ISBN: 978-1-4020-7782-1
eBook Packages: Springer Book Archive