论文标题
关于投票分类器的利润和概括
On Margins and Generalisation for Voting Classifiers
论文作者
论文摘要
我们研究了对分类器的有限集合的多数投票的概括特性，从而通过PAC-Bayes理论证明了基于利润的概括范围。这些为许多分类任务提供了最先进的保证。我们的中心结果利用了Zantedeschi等人最近研究的Dirichlet后代。 [2021]用于培训投票分类器；与这项工作相反，我们的界限适用于通过利润率使用非随机票。我们的贡献增加了Schapire等人提出的“边缘理论”的辩论。 [1998]用于集合分类器的概括。
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.
