Universal Consistency and Bloat in GP - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle Year : 2006

Universal Consistency and Bloat in GP

Sylvain Gelly
  • Function : Author
  • PersonId : 836546
Olivier Teytaud
Marc Schoenauer

Abstract

In this paper, we provide an analysis of Genetic Programming (GP) from the Statistical Learning Theory viewpoint in the scope of symbolic regression. Firstly, we are interested in Universal Consistency, i.e. the fact that the solution minimizing the empirical error does converge to the best possible error when the number of examples goes to infinity, and secondly, we focus our attention on the uncontrolled growth of program length (i.e. bloat), which is a well-known problem in GP. Results show that (1) several kinds of code bloats may be identified and that (2) Universal consistency can be obtained as well as avoiding bloat under some con- ditions. We conclude by describing an ad hoc method that makes it possible simultaneously to avoid bloat and to ensure universal consistency.
Fichier principal
Vignette du fichier
riabloat.pdf (173.82 Ko) Télécharger le fichier
Loading...

Dates and versions

inria-00112840 , version 1 (10-11-2006)

Identifiers

  • HAL Id : inria-00112840 , version 1

Cite

Sylvain Gelly, Olivier Teytaud, Nicolas Bredeche, Marc Schoenauer. Universal Consistency and Bloat in GP. Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, 2006. ⟨inria-00112840⟩
417 View
455 Download

Share

Gmail Facebook X LinkedIn More