Sciweavers

Share
MPC
2015
Springer

Generalized alternating direction method of multipliers: new theoretical insights and applications

4 years 10 months ago
Generalized alternating direction method of multipliers: new theoretical insights and applications
Recently, the alternating direction method of multipliers (ADMM) has received intensive attention from a broad spectrum of areas. The generalized ADMM (GADMM) proposed by Eckstein and Bertsekas is an efficient and simple acceleration scheme of ADMM. In this paper, we take a deeper look at the linearized version of GADMM where one of its subproblems is approximated by a linearization strategy. This linearized version is particularly efficient for a number of applications arising from different areas. Theoretically, we show the worst-case O(1/k) convergence rate measured by the iteration complexity (k represents the iteration counter) in both the ergodic and a nonergodic senses for the linearized version of GADMM. Numerically, we demonstrate the efficiency of this linearized version of GADMM by some rather new and core applications in statistical learning. Code packages in Matlab for these applications are also developed.
Ethan X. Fang, Bingsheng He, Han Liu, Xiaoming Yua
Added 15 Apr 2016
Updated 15 Apr 2016
Type Journal
Year 2015
Where MPC
Authors Ethan X. Fang, Bingsheng He, Han Liu, Xiaoming Yuan
Comments (0)
books