ABSTRACT
Genetic programming (GP) is a very successful type of learning algorithm that is hard to understand from a theoretical point of view. With this paper we contribute to the computational complexity analysis of genetic programming that has been started recently. We analyze GP in the well-known PAC learning framework and point out how it can observe quality changes in the the evolution of functions by random sampling. This leads to computational complexity bounds for a linear GP algorithm for perfectly learning any member of a simple class of linear pseudo-Boolean functions. Furthermore, we show that the same algorithm on the functions from the same class finds good approximations of the target function in less time.
- S. Droste, T. Jansen, and I. Wegener. On the analysis of the (1+1) evolutionary algorithm. Theoretical Computer Science, 276:51--81, 2002. Google ScholarDigital Library
- G. Durrett, F. Neumann, and U.-M. O'Reilly. Computational complexity analysis of simple genetic programming on two problems modeling isolated program semantics. In Proc. of FOGA'11, pages 69--80. ACM, 2011. Google ScholarDigital Library
- V. Feldman. Evolvability from learning algorithms. In Proc. of STOC'08, pages 619--628. ACM, 2008. Google ScholarDigital Library
- V. Feldman. A complete characterization of statistical query learning with applications to evolvability. In Proc. of FOCS'09, pages 375--384. IEEE, 2009. Google ScholarDigital Library
- C. Ferreira. Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence, volume 21 of Studies in Computational Intelligence. Springer, 2006. Google ScholarDigital Library
- D. E. Goldberg and U.-M. O'Reilly. Where does the good stuff go, and why? how contextual semantics influences program structure in simple genetic programming. In EuroGP'98, pages 16--36. Springer, 1998. Google ScholarDigital Library
- J. R. Koza. Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge, MA, USA, 1992. Google ScholarDigital Library
- I. Kushchu. Genetic programming and evolutionary generalization. IEEE Trans. Evolutionary Computation, 6:431--442, 2002. Google ScholarDigital Library
- H. Mühlenbein. How genetic algorithms really work: mutation and hillclimbing. In Proc. of PPSN'92, pages 15--26. Elsevier, 1992.Google Scholar
- F. Neumann and C. Witt. Bioinspired Computation in Combinatorial Optimization -- Algorithms and Their Computational Complexity. Springer, 2010. Google ScholarDigital Library
- R. Poli, W. B. Langdon, and N. F. McPhee. A Field Guide to Genetic Programming. lulu.com, 2008. Google ScholarDigital Library
- R. Poli, L. Vanneschi, W. B. Langdon, and N. F. McPhee. Theoretical results in genetic programming: the next ten years? Genetic Programming and Evolvable Machines, 11:285--320, 2010. Google ScholarDigital Library
- G. Rudolph. Convergence properties of evolutionary algorithms. Hamburg: Kovac, 1997.Google Scholar
- L. G. Valiant. A theory of the learnable. Commun. ACM, 27:1134--1142, 1984. Google ScholarDigital Library
- L. G. Valiant. Evolvability. J. ACM, 56, 2009. Google ScholarDigital Library
Index Terms
PAC learning and genetic programming
Recommendations
Bounding bloat in genetic programming
GECCO '17: Proceedings of the Genetic and Evolutionary Computation ConferenceWhile many optimization problems work with a fixed number of decision variables and thus a fixed-length representation of possible solutions, genetic programming (GP) works on variable-length representations. A naturally occurring problem is that of ...
Runtime analysis of mutation-based geometric semantic genetic programming on boolean functions
FOGA XII '13: Proceedings of the twelfth workshop on Foundations of genetic algorithms XIIGeometric Semantic Genetic Programming (GSGP) is a recently introduced form of Genetic Programming (GP), rooted in a geometric theory of representations, that searches directly the semantic space of functions/programs, rather than the space of their ...
Neural network crossover in genetic algorithms using genetic programming
AbstractThe use of genetic algorithms (GAs) to evolve neural network (NN) weights has risen in popularity in recent years, particularly when used together with gradient descent as a mutation operator. However, crossover operators are often omitted from ...
Comments