Maximal width learning of binary functions

11 years 3 hour ago
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
Martin Anthony, Joel Ratsaby
Added 30 Jan 2011
Updated 30 Jan 2011
Type Journal
Year 2010
Where TCS
Authors Martin Anthony, Joel Ratsaby
Comments (0)