Skip to yearly menu bar Skip to main content


Poster

On Margins and Generalisation for Voting Classifiers

Felix Biggs · Valentina Zantedeschi · Benjamin Guedj

Hall J (level 1) #935

Keywords: [ ensemble learning ] [ Margins ] [ Generalisation bounds ] [ Majority votes ] [ Aggregation of experts ] [ PAC-Bayes ]


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.

Chat is not available.