Sciweavers

COLT
2005
Springer

Ranking and Scoring Using Empirical Risk Minimization

13 years 9 months ago
Ranking and Scoring Using Empirical Risk Minimization
A general model is proposed for studying ranking problems. We investigate learning methods based on empirical minimization of the natural estimates of the ranking risk. The empirical estimates are of the form of a U-statistic. Inequalities from the theory of U-statistics and Uprocesses are used to obtain performance bounds for the empirical risk minimizers. Convex risk minimization methods are also studied to give a theoretical framework for ranking algorithms based on boosting and support vector machines. Just like in binary classification, fast rates of convergence are achieved under certain noise assumption. General sufficient conditions are proposed in several special cases that guarantee fast rates of convergence.
Stéphan Clémençon, Gáb
Added 29 Jun 2010
Updated 29 Jun 2010
Type Conference
Year 2005
Where COLT
Authors Stéphan Clémençon, Gábor Lugosi, Nicolas Vayatis
Comments (0)