TY - JOUR
T1 - Convergence of multi-block Bregman ADMM for nonconvex composite problems
AU - Wang, Fenghui
AU - Cao, Wenfei
AU - Xu, Zongben
N1 - Publisher Copyright:
© 2018, Science China Press and Springer-Verlag GmbH Germany, part of Springer Nature.
PY - 2018/12/1
Y1 - 2018/12/1
N2 - 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.
AB - 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.
KW - Bregman distance
KW - K-L inequality
KW - alternating direction method
KW - nonconvex regularization
KW - subanalytic function
UR - https://www.scopus.com/pages/publications/85049319141
U2 - 10.1007/s11432-017-9367-6
DO - 10.1007/s11432-017-9367-6
M3 - 文章
AN - SCOPUS:85049319141
SN - 1674-733X
VL - 61
JO - Science China Information Sciences
JF - Science China Information Sciences
IS - 12
M1 - 122101
ER -