Centre for Discrete and Applicable Mathematics
	CDAM Research Report, LSE-CDAM-99-07 August 1999

Abstract

This paper concerns the use of real-valued functions for binary classification problems. Previous work in this area has concentrated on using as an error estimate the `resubstitution' error (that is, the empirical error of a classifier on the training sample) or its derivatives. However, in practice, cross-validation and related techniques are more popular. Here, we analyse theoretically the accuracy of the holdout and cross-validation estimators for the case where real-valued functions are used as classifiers. We then introduce two new error estimation techniques, which we call the adaptive holdout est imate and the adaptive cross-validation estimate, and we perform similar analyses for these. Finally, we show how our results can be applied to certain types of neural network.

A compressed (gzip) PostScript file (79 kB) with the full contents of this report can be downloaded by clicking here.

Alternatively, if you like a free hard copy of this report, please send the number of this report, LSE-CDAM-99-07, together with your name and postal address to:

		CDAM Research Reports Series Centre for Discrete and Applicable Mathematics London School of Economics Houghton Street London WC2A 2AE, U.K.
		Phone: +44(0)-171-955 7732. Fax: +44(0)-171-955 6877. Email: info@maths.lse.ac.uk

		Introduction to the CDAM Research Report Series.
		CDAM Homepage.

Last changed: Wed 9 Feb 2005
For comments go to: http://www.maths.lse.ac.uk/webmaster.html