An analysis of the distribution of swapped subtree sizes in tree-based genetic programming

This paper analyses the distribution of swapped subtree sizes involved in crossover events in approximations of an optimal crossover operator that allows the root node to be crossed over. The goal is to examine how the offspring search space can be effectively reduced for given parents. It concludes that good crossover events have a strong preference for the roots of the parent programs and for nodes with small subtrees. This paper also quantifies the ability of crossover to optimise offspring fitness, and concludes that this ability is far below what was expected.

[1]  Walter Alden Tackett,et al.  Recombination, selection, and the genetic construction of computer programs , 1994 .

[2]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[3]  Kumar Chellapilla,et al.  Evolving computer programs without subtree crossover , 1997, IEEE Trans. Evol. Comput..

[4]  Peter Nordin,et al.  Complexity Compression and Evolution , 1995, ICGA.

[5]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[6]  Philippe Collard,et al.  Size Control with Maximum Homologous Crossover , 2005, Artificial Evolution.

[7]  P. Nordin,et al.  Explicitly defined introns and destructive crossover in genetic programming , 1996 .

[8]  Peter J. Angeline,et al.  Type Inheritance in Strongly Typed Genetic Programming , 1996 .

[9]  Riccardo Poli,et al.  On the Search Properties of Different Crossover Operators in Genetic Programming , 2001 .

[10]  Mengjie Zhang,et al.  A Study of Good Predecessor Programs for Reducing Fitness Evaluation Cost in Genetic Programming , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[11]  Mengjie Zhang,et al.  An analysis of depth of crossover points in tree-based Genetic Programming , 2007, 2007 IEEE Congress on Evolutionary Computation.

[12]  Patrik D'haeseleer,et al.  Context preserving crossover in genetic programming , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[13]  Conor Ryan,et al.  A Less Destructive, Context-Aware Crossover Operator for GP , 2006, EuroGP.

[14]  Peter J. Angeline,et al.  Two self-adaptive crossover operators for genetic programming , 1996 .

[15]  Lee Spector,et al.  A Revised Comparison of Crossover and Mutation in Genetic Programming , 1998 .

[16]  Mengjie Zhang,et al.  Not-Sampled Issue and Round-Replacement Tournament Selection , 2007 .

[17]  Lee Spector,et al.  Size Control Via Size Fair Genetic Operators In The PushGP Genetic Programming System , 2002, GECCO.

[18]  Una-May O'Reilly,et al.  Program Search with a Hierarchical Variable Lenght Representation: Genetic Programming, Simulated Annealing and Hill Climbing , 1994, PPSN.

[19]  Justinian P. Rosca,et al.  Learning by adapting representations in genetic programming , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[20]  Hitoshi Iba,et al.  A self-tuning mechanism for depth-dependent crossover , 1999 .

[21]  Peter J. Angeline,et al.  On Using Syntactic Constraints with Genetic Programming , 1996 .

[22]  Mengjie Zhang,et al.  An analysis of constructive crossover and selection pressure in genetic programming , 2007, GECCO '07.

[23]  Riccardo Poli,et al.  Backward-chaining evolutionary algorithms , 2006, Artif. Intell..

[24]  William B. Langdon,et al.  Size fair and homologous tree genetic programming crossovers , 1999 .