Measuring bloat, overfitting and functional complexity in genetic programming

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{Vanneschi:2010:gecco,

• author = "Leonardo Vanneschi and Mauro Castelli and Sara Silva",
• title = "Measuring bloat, overfitting and functional complexity in genetic programming",
• booktitle = "GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computation",
• year = "2010",
• editor = "Juergen Branke and Martin Pelikan and Enrique Alba and Dirk V. Arnold and Josh Bongard and Anthony Brabazon and Juergen Branke and Martin V. Butz and Jeff Clune and Myra Cohen and Kalyanmoy Deb and Andries P Engelbrecht and Natalio Krasnogor and Julian F. Miller and Michael O'Neill and Kumara Sastry and Dirk Thierens and Jano {van Hemert} and Leonardo Vanneschi and Carsten Witt",
• isbn13 = "978-1-4503-0072-8",
• pages = "877--884",
• keywords = "genetic algorithms, genetic programming",
• month = "7-11 " # jul,
• organisation = "SIGEVO",
• address = "Portland, Oregon, USA",
• DOI = "doi:10.1145/1830483.1830643",
• publisher = "ACM",
• publisher_address = "New York, NY, USA",
• abstract = "Recent contributions clearly show that eliminating bloat in a genetic programming system does not necessarily eliminate overfitting and vice-versa. This fact seems to contradict a common agreement of many researchers known as the minimum description length principle, which states that the best model is the one that minimises the amount of information needed to encode it. Another common agreement is that over fitting should be, in some sense, related to the functional complexity of the model. The goal of this paper is to define three measures to respectively quantify bloat, overfitting and functional complexity of solutions and show their suitability on a set of test problems including a simple bidimensional symbolic regression test function and two real-life multidimensional regression problems. The experimental results are encouraging and should pave the way to further investigation. Advantages and drawbacks of the proposed measures are discussed, and ways to improve them are suggested. In the future, these measures should be useful to study and better understand the relationship between bloat, overfitting and functional complexity of solutions.",
• notes = "Also known as \cite{1830643} GECCO-2010 A joint meeting of the nineteenth international conference on genetic algorithms (ICGA-2010) and the fifteenth annual genetic programming conference (GP-2010)",

}

Genetic Programming entries for Leonardo Vanneschi Mauro Castelli Sara Silva

Citations