Robust reductions from ranking to classification

Balcan, Maria-Florina, Bansal, Nikhil, Beygelzimer, Alina, Coppersmith, Don, Langford, John and Sorkin, Gregory B. ORCID: 0000-0003-4935-7820 (2008) Robust reductions from ranking to classification. Machine Learning, 72 (1-2). pp. 139-153. ISSN 0885-6125

Full text not available from this repository.

Abstract

We reduce ranking, as measured by the Area Under the Receiver Operating Characteristic Curve (AUC), to binary classification. The core theorem shows that a binary classification regret of r on the induced binary problem implies an AUC regret of at most 2r. This is a large improvement over approaches such as ordering according to regressed scores, which have a regret transform of r ↦ nr where n is the number of elements.

Item Type:	Article
Official URL:	http://www.springerlink.com/content/100309/
Additional Information:	© 2008 Springer Science+Business Media, LLC
Divisions:	Management
Subjects:	Q Science > QA Mathematics
Date Deposited:	13 Apr 2011 10:52
Last Modified:	11 Dec 2024 23:23
URI:	http://eprints.lse.ac.uk/id/eprint/35410

Actions (login required)

View Item