Convergence Revisit on Generalized Symmetric ADMM
Numerical Analysis
2019-06-20 v1 Numerical Analysis
Abstract
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. 70, 129-170 (2018)], 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.
Keywords
Cite
@article{arxiv.1906.07888,
title = {Convergence Revisit on Generalized Symmetric ADMM},
author = {Jianchao Bai and Xiaokai Chang and Jicheng Li and Fengmin Xu},
journal= {arXiv preprint arXiv:1906.07888},
year = {2019}
}
Comments
16 pages