Optimal rates of aggregation in classification under low noise assumption

Lecué, Guillaume

Bernoulli, Tome 13 (2007) no. 1, p. 1000-1022 / Harvested from Project Euclid

Résumé

In the same spirit as Tsybakov, 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.

Publié le : 2007-11-14
Classification: aggregation of classifiers, classification, optimal rates, margin

@article{1194625600,
     author = {Lecu\'e, Guillaume},
     title = {Optimal rates of aggregation in classification under low noise assumption},
     journal = {Bernoulli},
     volume = {13},
     number = {1},
     year = {2007},
     pages = { 1000-1022},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1194625600}
}

Lecué, Guillaume. Optimal rates of aggregation in classification under low noise assumption. Bernoulli, Tome 13 (2007) no. 1, pp.  1000-1022. http://gdmltest.u-ga.fr/item/1194625600/