Hostname: page-component-745bb68f8f-lrblm Total loading time: 0 Render date: 2025-02-06T04:37:55.957Z Has data issue: false hasContentIssue false
  • English
  • Français

Function Learning from Interpolation

Published online by Cambridge University Press:  01 May 2000

MARTIN ANTHONY  and
PETER L. BARTLETT
MARTIN ANTHONY
Affiliation:
Department of Mathematics, The London School of Economics and Political Science, Houghton Street, London WC2A 2AE, England (e-mail: m.anthony@lse.ac.uk)
PETER L. BARTLETT
Affiliation:
Department of Systems Engineering, Research School of Information Sciences and Engineering, The Australian National University, Canberra, 0200 Australia (e-mail: Peter.Bartlett@anu.edu.au)
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

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.

Type
Research Article
Information
Combinatorics, Probability and Computing , Volume 9 , Issue 3 , May 2000 , pp. 213 - 225
Copyright
2000 Cambridge University Press