Schema Analysis in Tree-Based Genetic Programming
In this chapter we adopt the concept of schemata from schema theory and use it to analyze population dynamics in genetic programming for symbolic regression. We define schemata as tree-based wildcard patterns and we empirically measure their frequencies in the population at each generation. Our methodology consists of two steps: in the first step we generate schemata based on genealogical information about crossover parents and their offspring, according to several possible schema definitions inspired from existing literature. In the second step, we calculate the matching individuals for each schema using a tree pattern matching algorithm. We test our approach on different problem instances and algorithmic flavors and we investigate the effects of different selection mechanisms on the identified schemata and their frequencies.
The work described in this paper was done within the COMET Project Heuristic Optimization in Production and Logistics (HOPL), #843532 funded by the Austrian Research Promotion Agency (FFG).
- 2.Altenberg, L., et al.: The evolution of evolvability in genetic programming. Advances in genetic programming 3, 47–74 (1994)Google Scholar
- 4.Banzhaf, W., Leier, A.: Evolution on neutral networks in genetic programming. In: Genetic programming theory and practice III, pp. 207–221. Springer (2006)Google Scholar
- 5.Burke, E., Gustafson, S., Kendall, G.: A survey and analysis of diversity measures in genetic programming. In: Proceedings of the 4th Annual Conference on Genetic and Evolutionary Computation, pp. 716–723. Morgan Kaufmann Publishers Inc. (2002)Google Scholar
- 8.Holland, J.H.: Adaptation in Natural and Artificial Systems. The University of Michigan Press (1975)Google Scholar
- 9.Hu, T., Banzhaf, W., Moore, J.H.: Population Exploration on Genotype Networks in Genetic Programming. In: Proceedings of the 13th International Conference on Parallel Problem Solving from Nature – PPSN XIII, 2014, pp. 424–433. Springer International Publishing, Cham (2014)Google Scholar
- 11.Krawiec, K., Wieloch, B.: Functional modularity for genetic programming. In: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation, GECCO ’09, pp. 995–1002. ACM, New York, NY, USA (2009). http://doi.acm.org/10.1145/1569901.1570037
- 12.Poli, R.: Hyperschema theory for gp with one-point crossover, building blocks, and some new results in ga theory. In: Genetic Programming, Proceedings of EuroGP 2000, pp. 15–16. Springer-Verlag (2000)Google Scholar
- 14.Poli, R.: A simple but theoretically-motivated method to control bloat in genetic programming. In: Proceedings of the 6th European Conference on Genetic Programming, EuroGP’03, pp. 204–217. Springer-Verlag, Berlin, Heidelberg (2003). http://dl.acm.org/citation.cfm?id=1762668.1762688 zbMATHGoogle Scholar
- 15.Poli, R., Langdon, W.B., Dignum, S.: Generalisation of the limiting distribution of program sizes in tree-based genetic programming and analysis of its effects on bloat. In: in GECCO 2007: Proceedings of the 9th Annual Conference on Genetic and Evolutionary, pp. 1588–1595. ACM Press (2007)Google Scholar
- 18.Poli, R., McPhee, N.F.: Covariant parsimony pressure for genetic programming. In: GECCO 2008: Proceedings of the 10th annual conference on Genetic and Evolutionary Computation, pp. 1267–1274. ACM Press (2008)Google Scholar
- 23.Wagner, S., Kronberger, G., Beham, A., Kommenda, M., Scheibenpflug, A., Pitzer, E., Vonolfen, S., Kofler, M., Winkler, S.M., Dorfer, V., Affenzeller, M.: Architecture and design of the heuristiclab optimization environment. Advanced Methods and Applications in Computational Intelligence, Topics in Intelligent Engineering and Informatics 6, 197–261 (2013)CrossRefGoogle Scholar
- 24.White, D.: An overview of schema theory. Computing Research Repository CoRR abs/1401.2651 (2014). http://arxiv.org/abs/1401.2651