On Margins and Generalisation for Voting Classifiers
From MaRDI portal
Publication:6401600
arXiv2206.04607MaRDI QIDQ6401600
Author name not available (Why is that?)
Publication date: 9 June 2022
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.
Has companion code repository: https://github.com/vzantedeschi/dirichlet-margin-bound
This page was built for publication: On Margins and Generalisation for Voting Classifiers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6401600)