English

Convergence of multi-block Bregman ADMM for nonconvex composite problems

Optimization and Control 2015-05-13 v1

Abstract

The alternating direction method with multipliers (ADMM) has been one of most powerful and successful methods for solving various composite problems. The convergence of the conventional ADMM (i.e., 2-block) for convex objective functions has been justified for a long time, and its convergence for nonconvex objective functions has, however, been established very recently. The multi-block ADMM, a natural extension of ADMM, is a widely used scheme and has also been found very useful in solving various nonconvex optimization problems. It is thus expected to establish convergence theory of the multi-block ADMM under nonconvex frameworks. In this paper we present a Bregman modification of 3-block ADMM and establish its convergence for a large family of nonconvex functions. We further extend the convergence results to the NN-block case (N3N \geq 3), which underlines the feasibility of multi-block ADMM applications in nonconvex settings. Finally, we present a simulation study and a real-world application to support the correctness of the obtained theoretical assertions.

Keywords

Cite

@article{arxiv.1505.03063,
  title  = {Convergence of multi-block Bregman ADMM for nonconvex composite problems},
  author = {Fenghui Wang and Wenfei Cao and Zongben Xu},
  journal= {arXiv preprint arXiv:1505.03063},
  year   = {2015}
}

Comments

25 pages, 2 figures

R2 v1 2026-06-22T09:32:48.659Z