Improved Margin Generalization Bounds for Voting Classifiers
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916773557698560 |
|---|---|
| author | Høgsgaard, Mikael Møller Larsen, Kasper Green |
| author_facet | Høgsgaard, Mikael Møller Larsen, Kasper Green |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16462 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improved Margin Generalization Bounds for Voting Classifiers Høgsgaard, Mikael Møller Larsen, Kasper Green Machine Learning Data Structures and Algorithms Statistics Theory 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. |
| title | Improved Margin Generalization Bounds for Voting Classifiers |
| topic | Machine Learning Data Structures and Algorithms Statistics Theory |
| url | https://arxiv.org/abs/2502.16462 |