Hedge algorithm and Dual Averaging schemes

Hedge algorithm and Dual Averaging schemes

0.00 Avg rating0 Votes
Article ID: iaor20133816
Volume: 77
Issue: 3
Start Page Number: 279
End Page Number: 289
Publication Date: Jun 2013
Journal: Mathematical Methods of Operations Research
Authors: ,
Keywords: machine learning
Abstract:

We show that the Hedge algorithm, a method that is widely used in Machine Learning, can be interpreted as a particular instance of Dual Averaging schemes, which have recently been introduced by Nesterov for regret minimization. Based on this interpretation, we establish three alternative methods of the Hedge algorithm: one in the form of the original method, but with optimal parameters, one that requires less a priori information, and one that is better adapted to the context of the Hedge algorithm. All our modified methods have convergence results that are better or at least as good as the performance guarantees of the vanilla method. In numerical experiments, our methods significantly outperform the original scheme.

Reviews

Required fields are marked *. Your email address will not be published.