Improved time complexity analysis of the Simple Genetic Algorithm

A runtime analysis of the Simple Genetic Algorithm (SGA) for the OneMax problem has recently been presented proving that the algorithm with population size µ ? n 1 / 8 - e requires exponential time with overwhelming probability. This paper presents an improved analysis which overcomes some limitations of the previous one. Firstly, the new result holds for population sizes up to µ ? n 1 / 4 - e which is an improvement up to a power of 2 larger. Secondly, we present a technique to bound the diversity of the population that does not require a bound on its bandwidth. Apart from allowing a stronger result, we believe this is a major improvement towards the reusability of the techniques in future systematic analyses of GAs. Finally, we consider the more natural SGA using selection with replacement rather than without replacement although the results hold for both algorithmic versions. Experiments are presented to explore the limits of the new and previous mathematical techniques.

[1]  Benjamin Doerr,et al.  Lessons from the black-box: fast crossover-based genetic algorithms , 2013, GECCO '13.

[2]  Thomas Jansen,et al.  A building-block royal road where crossover is provably essential , 2007, GECCO '07.

[3]  Pietro Simone Oliveto,et al.  On the runtime analysis of the Simple Genetic Algorithm , 2014, Theor. Comput. Sci..

[4]  Pietro Simone Oliveto,et al.  On the analysis of the simple genetic algorithm , 2012, GECCO '12.

[5]  Anne Auger,et al.  Theory of Randomized Search Heuristics: Foundations and Recent Developments , 2011, Theory of Randomized Search Heuristics.

[6]  Pietro Simone Oliveto,et al.  Analysis of population-based evolutionary algorithms for the vertex cover problem , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[7]  Thomas Jansen,et al.  Analyzing Evolutionary Algorithms: The Computer Science Perspective , 2012 .

[8]  Per Kristian Lehre,et al.  Black-Box Search by Unbiased Variation , 2010, GECCO '10.

[9]  P. A. P. Moran,et al.  An introduction to probability theory , 1968 .

[10]  Pietro Simone Oliveto,et al.  On the effectiveness of crossover for migration in parallel evolutionary algorithms , 2011, GECCO '11.

[11]  Per Kristian Lehre,et al.  Negative Drift in Populations , 2010, PPSN.

[12]  Timo Kötzing,et al.  Optimizing expected path lengths with ant colony optimization using fitness proportional update , 2013, FOGA XII '13.

[13]  B. Hajek.  Hitting-time and occupation-time bounds implied by drift analysis with applications , 1982, Advances in Applied Probability.

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

[15]  Pietro Simone Oliveto,et al.  Theoretical analysis of fitness-proportional selection: landscapes and efficiency , 2009, GECCO.

[16]  Frank Neumann,et al.  Bioinspired computation in combinatorial optimization: algorithms and their computational complexity , 2012, GECCO '12.

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

[18]  Dirk Sudholt,et al.  Crossover speeds up building-block assembly , 2012, GECCO '12.

[19]  Dirk Sudholt,et al.  The choice of the offspring population size in the (1,λ) EA , 2012, GECCO '12.

[20]  Thomas Jansen,et al.  Analyzing Evolutionary Algorithms , 2015, Natural Computing Series.

[21]  Frank Neumann,et al.  More effective crossover operators for the all-pairs shortest path problem , 2013, Theor. Comput. Sci..

[22]  Frank Neumann,et al.  Bioinspired computation in combinatorial optimization: algorithms and their computational complexity , 2010, GECCO '12.

[23]  Ingo Wegener,et al.  Real royal road functions--where crossover provably is essential , 2001, Discret. Appl. Math..

[24]  Frank Neumann,et al.  Rigorous analyses of fitness-proportional selection for optimizing linear functions , 2008, GECCO '08.

[25]  Dirk Sudholt,et al.  How crossover helps in pseudo-boolean optimization , 2011, GECCO '11.

[26]  Pietro Simone Oliveto,et al.  Improved runtime analysis of the simple genetic algorithm , 2013, GECCO '13.

[27]  Pietro Simone Oliveto,et al.  Simplified Drift Analysis for Proving Lower Bounds in Evolutionary Computation , 2008, Algorithmica.

[28]  Frank Neumann,et al.  More Effective Crossover Operators for the All-Pairs Shortest Path Problem , 2010, PPSN.

[29]  Per Kristian Lehre,et al.  Fitness-levels for non-elitist populations , 2011, GECCO '11.