Quantcast

Optimal rates of aggregation in classification under low noise assumption

Research paper by Guillaume Lecué

Indexed on: 04 Dec '07Published on: 04 Dec '07Published in: Mathematics - Statistics



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.