Comments on "Theoretical analysis of evolutionary algorithms with an infinite population size in continuous space. I. Basic properties of selection and mutation" [and reply]

This paper aims at establishing fundamental theoretical properties for a class of "genetic algorithms" in continuous space (GACS). The algorithms employ operators such as selection, crossover, and mutation in the framework of a multidimensional Euclidean space. The paper is divided into two parts. The first part concentrates on the basic properties associated with the selection and mutation operators. Recursive formulae for the GACS in the general infinite population case are derived and their validity is rigorously proven. A convergence analysis is presented for the classical case of a quadratic cost function. It is shown how the increment of the population mean is driven by its own diversity and follows a modified Newton's search. Sufficient conditions for monotonic increase of the population mean fitness are derived for a more general class of fitness functions satisfying a Lipschitz condition. The diversification role of the crossover operator is analyzed in Part II. The treatment adds much light to the understanding of the underlying mechanism of evolution-like algorithms. >

[1]  Günter Rudolph,et al.  Convergence analysis of canonical genetic algorithms , 1994, IEEE Trans. Neural Networks.

[2]  W. Ebeling,et al.  Boltzmann and Darwin strategies in complex optimization , 1987 .

[3]  King-Sun Fu,et al.  A variable structure automaton used as a multi-modal searching technique , 1965 .

[4]  Gunar E. Liepins,et al.  Punctuated Equilibria in Genetic Search , 1991, Complex Syst..

[5]  John Frank Charles Kingman,et al.  Coherent random walks arising in some genetical models , 1976, Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.

[6]  Marc Lipsitch,et al.  Adaptation on Rugged Landscapes Generated by Iterated Local Interactions of Neighboring Genes , 1991, ICGA.

[7]  Samuel H. Brooks.  A Discussion of Random Methods for Seeking Maxima , 1958 .

[8]  José Carlos Príncipe,et al.  A Simulated Annealing Like Convergence Theory for the Simple Genetic Algorithm , 1991, ICGA.

[9]  S Karlin,et al.  Central equilibria in multilocus systems. I. Generalized nonepistatic selection regimes. , 1979, Genetics.

[10]  Ray A. Jarvis,et al.  Adaptive Global Search by the Process of Competitive Evolution , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[11]  David E. Goldberg,et al.  Real-coded Genetic Algorithms, Virtual Alphabets, and Blocking , 1991, Complex Syst..

[12]  Atam P. Dhawan,et al.  Genetic Algorithms as Global Random Search Methods: An Alternative Perspective , 1995, Evolutionary Computation.

[13]  N. Baba,et al.  Global optimization of functions by the random optimization method , 1979 .

[14]  Larry J. Eshelman,et al.  On Crossover as an Evolutionarily Viable Strategy , 1991, ICGA.

[15]  A. E. Eiben,et al.  Global Convergence of Genetic Algorithms: A Markov Chain Analysis , 1990, PPSN.

[16]  Dean C. Karnopp,et al.  Random search techniques for optimization problems , 1963, Autom..

[17]  Alden H. Wright,et al.  Genetic Algorithms for Real Parameter Optimization , 1990, FOGA.

[18]  Thomas Bäck,et al.  A Survey of Evolution Strategies , 1991, ICGA.

[19]  S Karlin,et al.  Models of multifactorial inheritance: I. Multivariate formulations and basic convergence results. , 1979, Theoretical population biology.

[20]  William Feller,et al.  An Introduction to Probability Theory and Its Applications , 1951 .

[21]  M. Feldman,et al.  On the evolutionary effect of recombination. , 1970, Theoretical population biology.

[22]  W. Ebeling,et al.  Stochastic Theory of Molecular Replication Processes with Selection Character , 1977 .

[23]  Zbigniew Michalewicz,et al.  Handling Constraints in Genetic Algorithms , 1991, ICGA.

[24]  J. Kingman.  Uses of Exchangeability , 1978 .

[25]  J´nos Pintér,et al.  Convergence properties of stochastic optimization procedures , 1984 .

[26]  Iu M Svirezhev,et al.  Fundamentals of Mathematical Evolutionary Genetics , 1990 .

[27]  Werner Ebeling,et al.  Diffusion and reaction in random media and models of evolution processes , 1984 .

[28]  T. Maruyama,et al.  Stochastic Problems in Population Genetics , 1977 .

[29]  David E. Goldberg,et al.  Genetic Algorithms and Walsh Functions: Part I, A Gentle Introduction , 1989, Complex Syst..

[30]  L. Ginzburg,et al.  Multilocus population genetics: relative importance of selection and recombination. , 1980, Theoretical population biology.

[31]  Hans-Paul Schwefel,et al.  Numerical Optimization of Computer Models , 1982 .

[32]  Michael D. Vose,et al.  Modeling Simple Genetic Algorithms , 1995, Evolutionary Computation.

[33]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[34]  Michel Loève,et al.  Probability Theory I , 1977 .

[35]  Werner Ebeling.  Pattern dynamics and optimization by reaction diffusion systems , 1986 .

[36]  Francesco Zirilli,et al.  A global optimization algorithm using stochastic differential equations , 1988, TOMS.

[37]  Gunar E. Liepins,et al.  Polynomials, Basis Sets, and Deceptiveness in Genetic Algorithms , 1991, Complex Syst..

[38]  S Karlin,et al.  The reduction property for central polymorphisms in nonepistatic systems. , 1982, Theoretical population biology.

[39]  David E. Goldberg,et al.  Genetic Algorithms and Walsh Functions: Part II, Deception and Its Analysis , 1989, Complex Syst..

[40]  Heinz Mühlenbein,et al.  Evolution algorithms in combinatorial optimization , 1988, Parallel Comput..

[41]  S Karlin,et al.  Principles of polymorphism and epistasis for multilocus systems. , 1979, Proceedings of the National Academy of Sciences of the United States of America.

[42]  H. Haario,et al.  Simulated annealing process in general state space , 1991, Advances in Applied Probability.

[43]  Darrell Whitley,et al.  The Travelling Salesman and Sequence Scheduling: Quality Solutions using Genetic Edge Recombination , 1990 .

[44]  S. Kassam.  Signal Detection in Non-Gaussian Noise , 1987 .

[45]  I. Eshel,et al.  On evolution in a population with an infinite number of types. , 1971, Theoretical population biology.

[46]  S. M. Ermakov,et al.  On Random Search for a Global Extremum , 1984 .

[47]  Roger J.-B. Wets,et al.  Minimization by Random Search Techniques , 1981, Math. Oper. Res..

[48]  T. Ohta,et al.  Theoretical aspects of population genetics. , 1972, Monographs in population biology.

[49]  S. Karlin.  Equilibrium behavior of population genetic models with non-random mating. , 1968 .

[50]  H. Chernoff,et al.  Central Limit Theorems for Interchangeable Processes , 1958, Canadian Journal of Mathematics.

[51]  R. Brady.  Optimization strategies gleaned from biological evolution , 1985, Nature.

[52]  David B. Fogel,et al.  Evolving artificial intelligence , 1992 .

[53]  W. Ewens.  Mathematical Population Genetics , 1980 .

[54]  Kalyanmoy Deb,et al.  A Comparative Analysis of Selection Schemes Used in Genetic Algorithms , 1990, FOGA.

[55]  J. S. Gale,et al.  Theoretical Population Genetics , 1990, Springer Netherlands.

[56]  Francesco Palmieri,et al.  Analyses of the genetic algorithms in the continuous space , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[57]  Samuel Karlin,et al.  Analysis of central equilibria in multilocus systems: A generalized symmetric viability regime☆ , 1981 .