PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Maximal width learning of binary functions
Martin Anthony and Joel Ratsaby
Theoretical Computer Science Volume 411, pp. 138-147, 2010.

Abstract

This paper concerns learning binary-valued functions defined on \mathbb{R}, and investigates how a particular type of `regularity' of hypotheses can be used to obtain better generalization error bounds. We derive error bounds that depend on the sample width (a notion analagous to that of sample margin for real-valued functions). This motivates learning algorithms that seek to maximize sample width.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:6004
Deposited By:Martin Anthony
Deposited On:08 March 2010