In this paper we establish a new margin-based generalization bound for voting classifiers, refining existing results and yielding tighter generalization guarantees for widely used boosting algorithms such as AdaBoost (Freund and Schapire, 1997). Furthermore, the new margin-based generalization bound enables the derivation of an optimal weak-to-strong learner: a Majority-of-3 large-margin classifiers with an expected error matching the theoretical lower bound. This result provides a more natural alternative to the Majority-of-5 algorithm by (Høgsgaard et al. 2024) , and matches the Majority-of-3 result by (Aden-Ali et al. 2024) for the realizable prediction model.
View on arXiv@article{høgsgaard2025_2502.16462,
title={ Improved Margin Generalization Bounds for Voting Classifiers },
author={ Mikael Møller Høgsgaard and Kasper Green Larsen },
journal={arXiv preprint arXiv:2502.16462},
year={ 2025 }
}