Efficient Learning of Ensembles with QuadBoost
Machine Learning
2015-11-23 v5
Abstract
We first present a general risk bound for ensembles that depends on the Lp norm of the weighted combination of voters which can be selected from a continuous set. We then propose a boosting method, called QuadBoost, which is strongly supported by the general risk bound and has very simple rules for assigning the voters' weights. Moreover, QuadBoost exhibits a rate of decrease of its empirical error which is slightly faster than the one achieved by AdaBoost. The experimental results confirm the expectation of the theory that QuadBoost is a very efficient method for learning ensembles.
Cite
@article{arxiv.1506.02535,
title = {Efficient Learning of Ensembles with QuadBoost},
author = {Louis Fortier-Dubois and François Laviolette and Mario Marchand and Louis-Emile Robitaille and Jean-Francis Roy},
journal= {arXiv preprint arXiv:1506.02535},
year = {2015}
}
Comments
9 pages