Improved Margin Generalization Bounds for Voting Classifiers
This work provides improved theoretical guarantees for voting classifiers, which is incremental as it refines prior bounds and offers a more natural alternative to existing algorithms.
The paper establishes a new margin-based generalization bound for voting classifiers, refining existing results and yielding tighter guarantees for boosting algorithms like AdaBoost, and enables the derivation of an optimal weak-to-strong learner with an expected error matching the theoretical lower bound.
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.