Hedge algorithm and Dual Averaging schemes

被引：2

作者：

Baes, Michel ^{[1
]}

Buergisser, Michael ^{[1
]}

机构：

[1] ETH, Inst Operat Res, CH-8092 Zurich, Switzerland

来源：

MATHEMATICAL METHODS OF OPERATIONS RESEARCH | 2013年 / 77卷 / 03期

关键词：

First-order methods; Hedge algorithm; Dual Averaging methods; Convex optimization;

D O I：

10.1007/s00186-012-0418-1

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

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.

引用

页码：279 / 289

页数：11