Function learning from interpolation

Anthony, Martin and Bartlett, Peter L. (2000) Function learning from interpolation. Combinatorics, probability and computing, 9 (3). pp. 213-225. ISSN 0963-5483

Preview

PDF - Published Version Download (470Kb) | Preview

• LSE expert's profile
• Published Item

Abstract

In this paper, we study a statistical property of classes of real-valued functions that we call approximation from interpolated examples. We derive a characterization of function classes that have this property, in terms of their ‘fat-shattering function’, a notion that has proved useful in computational learning theory. The property is central to a problem of learning real-valued functions from random examples in which we require satisfactory performance from every algorithm that returns a function which approximately interpolates the training examples.

Item Type:	Article
Official URL:	http://journals.cambridge.org/action/displayJourna...
Additional Information:	© 2000 Cambridge University Press
Library of Congress subject classification:	Q Science > QA Mathematics
Sets:	Departments > Mathematics
Rights:	http://www.lse.ac.uk/library/rights/LSERO.htm
URL:	http://eprints.lse.ac.uk/7623/

Actions (login required)

Record administration - authorised staff only