文章基本信息

标题：Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization
本地全文：下载
作者：Anatoli Juditsky ; Yuri Nesterov;
期刊名称：Stochastic Systems
印刷版ISSN：1946-5238
出版年度：2014
卷号：4
期号：1
页码：44-80
出版社：Institute for Operations Research and the Management Sciences (INFORMS), Applied Probability Society
摘要：We discuss non-Euclidean deterministic and stochastic algorithms for optimization problems with strongly and uniformly convex objectives. We provide accuracy bounds for the performance of these algorithms and design methods which are adaptive with respect to the parameters of strong or uniform convexity of the objective: in the case when the total number of iterations N is fixed, their accuracy coincides, up to a logarithmic in N factor with the accuracy of optimal algorithms.
关键词：Strongly and uniformly convex optimization; non-Euclidean first order algorithms; large scale stochastic approximation