Anthony, Martin and Bartlett, Peter L.
(2000)
Function learning from interpolation.
Combinatorics, Probability and Computing, 9 (3).
pp. 213-225.
ISSN 0963-5483
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.
Actions (login required)
![View Item View Item](/style/images/action_view.png) |
View Item |