Quantifying accuracy of learning via sample width

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2013) Quantifying accuracy of learning via sample width. In: 2013 IEEE Symposium on Foundations of Computational Intelligence (FOCI). IEEE, Singapore, Singapore, pp. 84-90. ISBN 9781467359016

Full text not available from this repository.

• Author
• Publisher

Abstract

In a recent paper, the authors introduced the notion of sample width for binary classifiers defined on the set of real numbers. It was shown that the performance of such classifiers could be quantified in terms of this sample width. This paper considers how to adapt the idea of sample width so that it can be applied in cases where the classifiers are defined on some finite metric space. We discuss how to employ a greedy set-covering heuristic to bound generalization error. Then, by relating the learning problem to one involving certain graph-theoretic parameters, we obtain generalization error bounds that depend on the sample width and on measures of `density' of the underlying metric space.

Item Type:	Book Section
Official URL:	http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp...
Additional Information:	© 2013 IEEE
Divisions:	Mathematics
Subjects:	Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Date Deposited:	15 Mar 2013 15:54
Last Modified:	01 Nov 2024 04:38
URI:	http://eprints.lse.ac.uk/id/eprint/48770

Actions (login required)

View Item