NeurIPS 2022accept12 citations
On Margins and Generalisation for Voting Classifiers
Felix Biggs, Valentina Zantedeschi, Benjamin Guedj
Abstract
We study the generalisation properties of majority voting on finite ensembles of classifiers, proving margin-based generalisation bounds via the PAC-Bayes theory. These provide state-of-the-art guarantees on a number of classification tasks. Our central results leverage the Dirichlet posteriors studied recently by Zantedeschi et al. (2021) for training voting classifiers; in contrast to that work our bounds apply to non-randomised votes via the use of margins. Our contributions add perspective to the debate on the ``margins theory'' proposed by Schapire et al. (1998) for the generalisation of ensemble classifiers.
PAC-BayesGeneralisation boundsEnsemble learningMarginsMajority votesAggregation of experts
BibTeX
@inproceedings{
biggs2022on,
title={On Margins and Generalisation for Voting Classifiers},
author={Felix Biggs and Valentina Zantedeschi and Benjamin Guedj},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=xvLWypz8p8}
}