期刊
MATHEMATICAL PROGRAMMING
卷 103, 期 1, 页码 127-152出版社
SPRINGER
DOI: 10.1007/s10107-004-0552-5
关键词
non-smooth optimization; convex optimization; optimal methods; complexity theory; structural optimization
In this paper we propose anew approach for constructing efficient schemes for non-smooth convex optimization. It is based on a special smoothing technique, which can be applied to functions with explicit max-structure. Our approach can be considered as an alternative to black-box minimization. From the viewpoint of efficiency estimates, we manage to improve the traditional bounds on the number of iterations of the gradient schemes from O (1/is an element of(2)) to O (1/is an element of), keeping basically the complexity of each iteration unchanged.
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