Large width nearest prototype classification on general distance spaces

Anthony, Martin ORCID: 0000-0002-7796-6044 and Ratsaby, Joel (2018) Large width nearest prototype classification on general distance spaces. Theoretical Computer Science, 738 (22). pp. 65-79. ISSN 0304-3975

Preview

Text - Accepted Version Download (490kB) | Preview

• Author

Abstract

In this paper we consider the problem of learning nearest-prototype classifiers in any finite distance space; that is, in any finite set equipped with a distance function. An important advantage of a distance space over a metric space is that the triangle inequality need not be satisfied, which makes our results potentially very useful in practice. We consider a family of binary classifiers for learning nearest-prototype classification on distance spaces, building on the concept of large-width learning which we introduced and studied in earlier works. Nearest-prototype is a more general version of the ubiquitous nearest-neighbor classifier: a prototype may or may not be a sample point. One advantage in the approach taken in this paper is that the error bounds depend on a 'width' parameter, which can be sample-dependent and thereby yield a tighter bound.

Item Type:	Article
Official URL:	https://www.sciencedirect.com/journal/theoretical-...
Additional Information:	© 2018 Elsevier B.V.
Divisions:	Mathematics
Subjects:	Q Science > QA Mathematics
Date Deposited:	27 Apr 2018 12:13
Last Modified:	11 Dec 2024 21:37
Funders:	Suntory and Toyota International Centres for Economics and Related Disciplines
URI:	http://eprints.lse.ac.uk/id/eprint/87680

Actions (login required)

View Item