Open Access
Translator Disclaimer
2013 Upper bounds and aggregation in bipartite ranking
Sylvain Robbiano
Electron. J. Statist. 7: 1249-1271 (2013). DOI: 10.1214/13-EJS805


One main focus of learning theory is to find optimal rates of convergence. In classification, it is possible to obtain optimal fast rates (faster than $n^{-1/2}$) in a minimax sense. Moreover, using an aggregation procedure, the algorithms are adaptive to the parameters of the class of distributions. Here, we investigate this issue in the bipartite ranking framework. We design a ranking rule by aggregating estimators of the regression function. We use exponential weights based on the empirical ranking risk. Under several assumptions on the class of distribution, we show that this procedure is adaptive to the margin parameter and smoothness parameter and achieves the same rates as in the classification framework. Moreover, we state a minimax lower bound that establishes the optimality of the aggregation procedure in a specific case.


Download Citation

Sylvain Robbiano. "Upper bounds and aggregation in bipartite ranking." Electron. J. Statist. 7 1249 - 1271, 2013.


Published: 2013
First available in Project Euclid: 29 April 2013

zbMATH: 1336.62068
MathSciNet: MR3056074
Digital Object Identifier: 10.1214/13-EJS805

Primary: 62C20 , 62F07
Secondary: 62G08

Keywords: Aggregation , Minimax rates , ranking

Rights: Copyright © 2013 The Institute of Mathematical Statistics and the Bernoulli Society


Back to Top