期刊
SIAM JOURNAL ON OPTIMIZATION
卷 27, 期 1, 页码 110-123出版社
SIAM PUBLICATIONS
DOI: 10.1137/16M1060182
关键词
convex optimization; structural optimization; fast gradient methods; coordinate descent methods; complexity bounds
资金
- Direction de la recherche scientifique - Communaute francaise de Belgique [14/19-060]
- Swiss Science Foundation (SNF)
In this paper we prove a new complexity bound for a variant of the accelerated coordinate descent method [Yu. Nesterov, SIAM T. Opttm., 22 (2012), pp. 341-362]. We show that this method often outperforms the standard fast gradient methods (FGM [Yu. Nesterov, Dokl. Akad. Nauk SSSR, 269 (1983), pp. 542-547; Math. Program. (A), 103 (2005), pp. 127-152]) on optimization problems with dense data. In many important situations, the computational expenses of oracle and method itself at each iteration of our scheme are perfectly balanced (both depend linearly on dimensions of the problem). As application examples, we consider unconstrained convex quadratic minimization and the problems arising in the smoothing technique [Nesterov, Math. Program. (A), 103 (2005), pp. 127-152]. On some special problem instances, the provable acceleration factor with respect to FGM can reach the square root of the number of variables. Our theoretical conclusions are confirmed by numerical experiments.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据