Convergence of multi-block Bregman ADMM for nonconvex composite problems

Research output: Contribution to journalArticlepeer-review

116 Scopus citations

Abstract

The alternating direction method with multipliers (ADMM) is one of the 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 stated 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 the convergence of the multi-block ADMM under nonconvex frameworks. In this paper, we first justify the convergence of 3-block Bregman ADMM. We next extend these results to the N-block case (N ≥ 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.

Original languageEnglish
Article number122101
JournalScience China Information Sciences
Volume61
Issue number12
DOIs
StatePublished - 1 Dec 2018

Keywords

  • Bregman distance
  • K-L inequality
  • alternating direction method
  • nonconvex regularization
  • subanalytic function

Fingerprint

Dive into the research topics of 'Convergence of multi-block Bregman ADMM for nonconvex composite problems'. Together they form a unique fingerprint.

Cite this