PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Square root penalty: adaptation to the margin in classification and in edge estimation
S.A. van de Geer and A.B. Tsybakov
The Annals of Statistics 2005.


We consider the problem of adaptation to the margin in binary classification. We suggest a penalized empirical risk minimization classifier that adaptively attains, up to a logarithmic factor, fast optimal rates of convergence for the excess risk, i.e.\ rates that can be faster than $n^{-1/2}$, where $n$ is the sample size. We show that our method also gives adaptive estimators for the problem of edge estimation.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
ID Code:450
Deposited By:Sara van de Geer
Deposited On:23 December 2004