Exponential weighting and oracle inequalities for projection methods
Statistics Theory
2012-06-20 v1 Statistics Theory
Abstract
We consider the problem of recovering an unknown vector from noisy data with the help of projection estimates. The goal is to find a convex combination of these estimates with the minimal risk. We study an aggregation method based on the so-called exponential weighting and provide a new upper bound for the mean square risk of this method.
Cite
@article{arxiv.1206.4285,
title = {Exponential weighting and oracle inequalities for projection methods},
author = {Yu. Golubev},
journal= {arXiv preprint arXiv:1206.4285},
year = {2012}
}