当前位置: X-MOL 学术Optim. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Primal-dual subgradient method for constrained convex optimization problems
Optimization Letters ( IF 1.3 ) Pub Date : 2021-04-05 , DOI: 10.1007/s11590-021-01728-x
Michael R. Metel , Akiko Takeda

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.



中文翻译:

约束凸优化问题的原始对偶次梯度法

本文考虑了一个一般的凸约束问题集,在该问题集下,函数不被假定为可微的,也没有Lipschitz连续的。我们的动机是找到一种简单的一阶方法,以最小的要求来解决各种凸优化问题。我们研究了这种情况下的加权对数平均方法(Nesterov in Math Programm 120(1):221–259,2009),并证明了它是一种最佳方法。

更新日期:2021-04-06
down
wechat
bug