Primal-dual subgradient method for constrained convex optimization problems

Primal-dual subgradient method for constrained convex optimization problems
复制标题

约束凸优化问题的原对偶次梯度法

DOI:
10.1007/s11590-021-01728-x
复制
发表时间:
2021
影响因子:
1.6
通讯作者:
Akiko Takeda
Akiko Takeda
中科院分区:
数学4区
文献类型:
--
作者:
Michael R. Metel;Akiko Takeda

文献摘要

相似文献

本文考虑一般的凸约束问题集,其中函数既不是可微的,也不是Lipschitz连续的。我们的动机是找到一种简单的一阶方法,以最小的要求解决广泛的凸优化问题。在这种情况下,我们研究了加权对偶平均法(数学规划120(1):221-259,2009),证明了它是一种最优的方法。
This paper considers a general convex constrained problem setting where functions are not assumed to be differentiable nor Lipschitz continuous. Our motivation is in finding a simple first-order method for solving a wide range of convex optimization problems with minimal requirements. We study the method of weighted dual averages (Nesterov in Math Programm 120(1): 221–259, 2009) in this setting and prove that it is an optimal method.