Convergence revisit on generalized symmetric ADMM
Convergence revisit on generalized symmetric ADMM
复制标题
DOI：
10.1080/02331934.2019.1704754
复制
发表时间：
2019-06
期刊：
影响因子：
2.2
通讯作者：
Jianchao Bai;Xiaokai Chang;Jicheng Li;Fengmin Xu
中科院分区：
文献类型：
--
作者：
Jianchao Bai;Xiaokai Chang;Jicheng Li;Fengmin Xu
In this note, we show a sublinear nonergodic convergence rate for the algorithm developed in Bai et al. [Generalized symmetric ADMM for separable convex optimization. Comput Optim Appl. 2018;70:129–170], as well as its linear convergence under assumptions that the sub-differential of each component objective function is piecewise linear and all the constraint sets are polyhedra. These remaining convergence results are established for the stepsize parameters of dual variables belonging to a special isosceles triangle region, which aims to strengthen our understanding for convergence of the generalized symmetric ADMM.
