Open Access
Translator Disclaimer
April 2008 Ranking and Empirical Minimization of U-statistics
Stéphan Clémençon, Gábor Lugosi, Nicolas Vayatis
Ann. Statist. 36(2): 844-874 (April 2008). DOI: 10.1214/009052607000000910

Abstract

The problem of ranking/ordering instances, instead of simply classifying them, has recently gained much attention in machine learning. In this paper we formulate the ranking problem in a rigorous statistical framework. The goal is to learn a ranking rule for deciding, among two instances, which one is “better,” with minimum ranking risk. Since the natural estimates of the risk are of the form of a U-statistic, results of the theory of U-processes are required for investigating the consistency of empirical risk minimizers. We establish, in particular, a tail inequality for degenerate U-processes, and apply it for showing that fast rates of convergence may be achieved under specific noise assumptions, just like in classification. Convex risk minimization methods are also studied.

Citation

Download Citation

Stéphan Clémençon. Gábor Lugosi. Nicolas Vayatis. "Ranking and Empirical Minimization of U-statistics." Ann. Statist. 36 (2) 844 - 874, April 2008. https://doi.org/10.1214/009052607000000910

Information

Published: April 2008
First available in Project Euclid: 13 March 2008

zbMATH: 1181.68160
MathSciNet: MR2396817
Digital Object Identifier: 10.1214/009052607000000910

Subjects:
Primary: 60C05, 60E15, 60G25, 68Q32

Rights: Copyright © 2008 Institute of Mathematical Statistics

JOURNAL ARTICLE
31 PAGES


SHARE
Vol.36 • No. 2 • April 2008
Back to Top