On improving genetic programming for symbolic regression

This paper reports an improvement to genetic programming (GP) search for the symbolic regression domain, based on an analysis of dissimilarity and mating. GP search is generally difficult to characterise for this domain, preventing well motivated algorithmic improvements. We first examine the ability of various solutions to contribute to the search process. Further analysis highlights the numerous solutions produced during search with no change to solution quality. A simple algorithmic enhancement is made that reduces these events and produces a statistically significant improvement in solution quality. We conclude by verifying the generalisability of these results on several other regression instances

[1]  Graham Kendall,et al.  A Survey And Analysis Of Diversity Measures In Genetic Programming , 2002, GECCO.

[2]  Robert I. McKay,et al.  Fitness Sharing in Genetic Programming , 2000, GECCO.

[3]  Ari Juels,et al.  Stochastic Hillclimbing as a Baseline Method for , 1994 .

[4]  Jason M. Daida,et al.  Visualizing the loss of diversity in genetic programming , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[5]  Jason M. Daida,et al.  What Makes a Problem GP-Hard? Analysis of a Tunably Difficult Problem in Genetic Programming , 1999, Genetic Programming and Evolvable Machines.

[6]  Graham Kendall,et al.  Advanced Population Diversity Measures in Genetic Programming , 2002, PPSN.

[7]  Riccardo Poli,et al.  Foundations of Genetic Programming , 1999, Springer Berlin Heidelberg.

[8]  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.

[9]  Anikó Ekárt,et al.  Maintaining the Diversity of Genetic Programs , 2002, EuroGP.

[10]  Maarten Keijzer,et al.  Improving Symbolic Regression with Interval Arithmetic and Linear Scaling , 2003, EuroGP.

[11]  Graham Kendall,et al.  Diversity in genetic programming: an analysis of measures and correlation with fitness , 2004, IEEE Transactions on Evolutionary Computation.

[12]  Jianjun Hu,et al.  Structure Fitness Sharing (SFS) For Evolutionary Design By Genetic Programming , 2002, GECCO.

[13]  C. Fernandes,et al.  A study on non-random mating and varying population size in genetic algorithms using a royal road function , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[14]  Graham Kendall,et al.  Problem Difficulty and Code Growth in Genetic Programming , 2004, Genetic Programming and Evolvable Machines.

[15]  E. Goodman,et al.  Continuous Hierarchical Fair Competition Model for Sustainable Innovation in Genetic Programming , 2003 .

[16]  Graham Kendall,et al.  Sampling of Unique Structures and Behaviours in Genetic Programming , 2004, EuroGP.

[17]  R. Collins.  Studies in artificial evolution , 1992 .

[18]  Kalyanmoy Deb,et al.  An Investigation of Niche and Species Formation in Genetic Function Optimization , 1989, ICGA.

[19]  Anikó Ekárt,et al.  A Metric for Genetic Programs and Fitness Sharing , 2000, EuroGP.

[20]  Edwin D. de Jong,et al.  Reducing bloat and promoting diversity using multi-objective methods , 2001 .

[21]  Wolfgang Banzhaf,et al.  Explicit Control of Diversity and Effective Variation Distance in Linear Genetic Programming , 2002, EuroGP.

[22]  Philippe Collard,et al.  Maximum Homologous Crossover for Linear Genetic Programming , 2003, EuroGP.

[23]  Robert I. McKay.  Partial functions in fitness-shared genetic programming , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

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

[25]  Steven M. Gustafson.  An analysis of diversity in genetic programming , 2004 .

[26]  Conor Ryan,et al.  Pygmies and civil servants , 1994 .