We prove the first generalization bound for large-margin halfspaces that is asymptotically tight in the tradeoff between the margin, the fraction of training points with the given margin, the failure probability and the number of training points.
@article{arxiv.2502.13692,
title = {Tight Generalization Bounds for Large-Margin Halfspaces},
author = {Kasper Green Larsen and Natascha Schalburg},
journal= {arXiv preprint arXiv:2502.13692},
year = {2025}
}