A Study of Good Predecessor Programs for Reducing Fitness Evaluation Cost in Genetic Programming

Huayang Xie, Mengjie Zhang, Peter Andreae

Abstract

Good Predecessor Programs (GPPs) are the ancestors of the best program found in a Genetic Programming (GP) evolution. This paper reports on an investigation into GPPs with the ultimate goal of reducing fitness evaluation cost in tree-based GP systems. A framework is developed for gathering information about GPPs and a series of experiments is conducted on a symbolic regression problem, a binary classification problem, and a multi-class classification program with increasing levels of difficulty in different domains. The analysis of the data shows that during evolution, GPPs typically constitute less than 33% of the total programs evaluated, and may constitute less than 5%. The analysis results further shows that in all evaluated programs, the proportion of GPPs is reduced by increasing tournament size and to a less extent, affected by population size. Problem difficulty seems to have no clear influence on the proportion of GPPs.
BibTeX
@inproceedings{xie2006study,
  author = {Huayang Xie and Mengjie Zhang and Peter Andreae},
  title = {{A Study of Good Predecessor Programs for Reducing Fitness Evaluation Cost in Genetic Programming}},
  booktitle = {IEEE CEC},
  year = {2006},
  doi = {10.1109/cec.2006.1688641},
}

Loading related content...

Figure