Optimal rates of aggregation in classification under low noise assumption
Statistics Theory
2007-12-04 v2 Statistics Theory
Abstract
In the same spirit as Tsybakov (2003), we define the optimality of an aggregation procedure in the problem of classification. Using an aggregate with exponential weights, we obtain an optimal rate of convex aggregation for the hinge risk under the margin assumption. Moreover we obtain an optimal rate of model selection aggregation under the margin assumption for the excess Bayes risk.
Cite
@article{arxiv.math/0603447,
title = {Optimal rates of aggregation in classification under low noise assumption},
author = {Guillaume Lecué},
journal= {arXiv preprint arXiv:math/0603447},
year = {2007}
}