Aggregation by exponential weighting and sharp oracle
Arnak Dalalyan and Alexandre Tsybakov
In: COLT 2007, 13-15 Jun 2007, San Diego, USA.
In the present paper, we study the problem of aggregation under the
squared loss in the model of regression with deterministic design.
We obtain sharp oracle inequalities for convex aggregates defined
via exponential weights, under general assumptions on the
distribution of errors and on the functions to aggregate. We show
how these results can be applied to derive a sparsity oracle