Learning by mirror averaging
A. Juditsky, P. Rigollet, A. B. Tsybakov
The Annals of Statistics · 2008 · Volume 36 · Issue 5
Abstract
Given a finite collection of estimators or classifiers, we study the problem of model selection type aggregation, that is, we construct a new estimator or classifier, called aggregate, which is nearly as good as the best among them with respect to a given risk criterion. We define our aggregate by a simple recursive procedure which solves an auxiliary stochastic linear programming problem related to the original nonlinear one and constitutes a special case of the mirror averaging algorithm. We show that the aggregate satisfies sharp oracle inequalities under some general assumptions. The results are applied to several problems including regression, classification and density estimation.
Keywords
62C20, 62G05, 62G08, 62G20, Aggregation, learning, mirror averaging, Model selection, Oracle inequalities, stochastic optimization
Enable JavaScript for citation tools and additional paper interactions.