Maximal width learning of binary functions

This paper concerns learning binary-valued functions defined on IR, 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 similar to that of sample margin for real-valued functions). This motivates learning algorithms that seek to maximize sample width. 1 

• Type: Journal
• Year: 2010
• Where: TCS
• Authors: Martin Anthony, Joel Ratsaby
• Keywords: Generalization Error, Sample Margin, Sample Width, TCS 2010, Theoretical Computer Science