Tight Generalization Bounds for Large-Margin Halfspaces

Kasper Green Larsen, Natascha Schalburg

Keywords: Learning theory, Generalization Bounds, Large-Margin Halfspaces, Rademacher complexity

TL;DR: We prove the first generalization bound for large-margin halfspaces that is asymptotically tight.

Abstract: 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.

Primary Area: Theory (e.g., control theory, learning theory, algorithmic game theory)

Submission Number: 12624