Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets
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_ | 1866917103733309440 |
|---|---|
| author | Larsen, Kasper Green Schalburg, Natascha |
| author_facet | Larsen, Kasper Green Schalburg, Natascha |
| contents | We prove the first margin-based generalization bound for voting classifiers, that is asymptotically tight in the tradeoff between the size of the hypothesis set, the margin, the fraction of training points with the given margin, the number of training samples and the failure probability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20407 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets Larsen, Kasper Green Schalburg, Natascha Machine Learning Statistics Theory We prove the first margin-based generalization bound for voting classifiers, that is asymptotically tight in the tradeoff between the size of the hypothesis set, the margin, the fraction of training points with the given margin, the number of training samples and the failure probability. |
| title | Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets |
| topic | Machine Learning Statistics Theory |
| url | https://arxiv.org/abs/2511.20407 |