An empirical study of functional complexity as an indicator of overfitting in Genetic Programming

Published in Conferences Papers
  1. Leonardo Trujillo, Sara Silva, Pierrick Legrand and Leonardo Vanneschi. An Empirical Study of Functional Complexity as an Indicator of Overfitting in Genetic Programming. In EuroGP. 2011, 262-273. BibTeX

    @inproceedings{DBLP:conf/eurogp/TrujilloSLV11,
    	author = "Leonardo Trujillo and Sara Silva and Pierrick Legrand and Leonardo Vanneschi",
    	title = "An Empirical Study of Functional Complexity as an Indicator of Overfitting in Genetic Programming",
    	booktitle = "EuroGP",
    	year = 2011,
    	pages = "262-273",
    	ee = "http://dx.doi.org/10.1007/978-3-642-20407-4_23",
    	crossref = "DBLP:conf/eurogp/2011",
    	bibsource = "DBLP, http://dblp.uni-trier.de"
    }
    
  2. Sara Silva, James A Foster, Miguel Nicolau, Penousal Machado and Mario Giacobini (eds.). Genetic Programming - 14th European Conference, EuroGP 2011, Torino, Italy, April 27-29, 2011. Proceedings 6621. Springer, 2011. BibTeX

    @proceedings{DBLP:conf/eurogp/2011,
    	editor = "Sara Silva and James A. Foster and Miguel Nicolau and Penousal Machado and Mario Giacobini",
    	title = "Genetic Programming - 14th European Conference, EuroGP 2011, Torino, Italy, April 27-29, 2011. Proceedings",
    	booktitle = "EuroGP",
    	publisher = "Springer",
    	series = "Lecture Notes in Computer Science",
    	volume = 6621,
    	year = 2011,
    	isbn = "978-3-642-20406-7",
    	ee = "http://dx.doi.org/10.1007/978-3-642-20407-4",
    	bibsource = "DBLP, http://dblp.uni-trier.de"
    }
    
Abstract

Recently, it has been stated that the complexity of a solution is a good indicator of the amount of overfitting it incurs. However, measuring the complexity of a program, in Genetic Programming, is not a trivial task. In this paper, we study the functional complexity and how it relates with overfitting on symbolic regression problems. We consider two measures of complexity, Slope-based Functional Complexity, inspired by the concept of curvature, and Regularity-based Functional Complexity based on the concept of Hölderian regularity. In general, both complexity measures appear to be poor indicators of program overfitting. However, results suggest that Regularity-based Functional Complexity could provide a good indication of overfitting in extreme cases.

Published in
Proceedings of the 14th European Conference on Genetic Programming
Volume 6621
Pages 262-273
http://link.springer.com/chapter/10.1007%2F978-3-642-20407-4_23
Date of conference
27-29 Abril 2011
ISSN
0302-9743
ISBN
978-3-642-20407-4
Feedback