Statistical distribution of the convergence time of evolutionary algorithms for long-path problems

The behavior of a (1+1)-ES process on Rudolph's binary long k paths is investigated extensively in the asymptotic framework with respect to string length l. First, the case of k=l/sup /spl alpha// is addressed. For /spl alpha//spl ges/1/2, we prove that the long k path is a long path for the (1+1)-ES in the sense that the process follows the entire path with no shortcuts, resulting in an exponential expected convergence time. For /spl alpha/<1/2, the expected convergence time is also exponential, but some shortcuts occur in the meantime that speed up the process. Next, in the case of constant k, the statistical distribution of convergence time is calculated, and the influence of population size is investigated for different (/spl mu/+/spl lambda/)-ES. The histogram of the first hitting time of the solution shows an anomalous peak close to zero, which corresponds to an exceptional set of events that speed up the expected convergence time with a factor of l/sup 2/. A direct consequence of this exceptional set is that performing independent (1+1)-ES processes proves to be more advantageous than any population-based (/spl mu/+/spl lambda/)-ES.

[1]  Feller William,et al.  An Introduction To Probability Theory And Its Applications , 1950 .

[2]  Melanie Mitchell,et al.  The royal road for genetic algorithms: Fitness landscapes and GA performance , 1991 .

[3]  Irene A. Stegun,et al.  Handbook of Mathematical Functions. , 1966 .

[4]  William Feller,et al.  An Introduction to Probability Theory and Its Applications , 1967 .

[5]  Debashish Chowdhury,et al.  Spin Glasses and Other Frustrated Systems , 1986 .

[6]  高山 一,et al.  D. Chowdhury: Spin Glasses and Other Frustrated Systems, World Scientific, Singapore, 1986, xiv+386ページ, 22.5×16cm, 5,023円. , 1987 .

[7]  Melanie Mitchell,et al.  Relative Building-Block Fitness and the Building Block Hypothesis , 1992, FOGA.

[8]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[9]  Bart Naudts,et al.  Candidate Longpaths for the Simple Genetic Algorithm , 1998, FOGA.

[10]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[11]  D. Stroock.  An Introduction to the Theory of Large Deviations , 1984 .

[12]  I. I. Gikhman,et al.  Introduction à la théorie des processus aléatoires , 1980 .

[13]  Colin R. Reeves,et al.  Are Long Path Problems Hard for Genetic Algorithms? , 1996, PPSN.

[14]  John H. Holland,et al.  When will a Genetic Algorithm Outperform Hill Climbing , 1993, NIPS.

[15]  Günter Rudolph,et al.  Convergence of non-elitist strategies , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[16]  P. Priouret,et al.  An introduction to the theory of large deviations , 1986 .

[17]  Kalyanmoy Deb,et al.  Long Path Problems , 1994, PPSN.