We study properties of Linear Genetic Programming (LGP) through several regression and classification benchmarks. In each problem, we decompose the results into bias and variance components, and explore the effect of varying certain key parameters on the overall error and its decomposed contributions. These parameters are the maximum program size, the initial population, and the function set used. We confirm and quantify several insights into the practical usage of GP, most notably that (a) the variance between runs is primarily due to initialization rather than the selection of training samples, (b) parameters can be reasonably optimized to obtain gains in efficacy, and (c) functions detrimental to evolvability are easily eliminated, while functions well-suited to the problem can greatly improve performance-therefore, larger and more diverse function sets are always preferable.
@article{bwmeta1.element.doi-10_1515_math-2016-0005,
author = {Taras Kowaliw and Ren\'e Doursat},
title = {Bias-variance decomposition in Genetic Programming},
journal = {Open Mathematics},
volume = {14},
year = {2016},
pages = {62-80},
zbl = {1346.62077},
language = {en},
url = {http://dml.mathdoc.fr/item/bwmeta1.element.doi-10_1515_math-2016-0005}
}
Taras Kowaliw; René Doursat. Bias-variance decomposition in Genetic Programming. Open Mathematics, Tome 14 (2016) pp. 62-80. http://gdmltest.u-ga.fr/item/bwmeta1.element.doi-10_1515_math-2016-0005/