Convergence of Bregman alternating direction method with multipliers for nonconvex composite problems
arXiv:1410.8625
Abstract
The alternating direction method with multipliers (ADMM) has been one of most powerful and successful methods for solving various convex or nonconvex composite problems that arise in the fields of image & signal processing and machine learning. In convex settings, numerous convergence results have been established for ADMM as well as its varieties. However, due to the absence of convexity, the convergence analysis of nonconvex ADMM is generally very difficult. In this paper we study the Bregman modification of ADMM (BADMM), which includes the conventional ADMM as a special case and often leads to an improvement of the performance of the algorithm. Under certain assumptions, we prove that the iterative sequence generated by BADMM converges to a stationary point of the associated augmented Lagrangian function. The obtained results underline the feasibility of ADMM in applications under nonconvex settings.
17 pages, 2 figures
Cited by in corpus (5)
- Convergence of multi-block Bregman ADMM for nonconvex composite problems
- An Empirical Study of ADMM for Nonconvex Problems
- Iteration-complexity of a Jacobi-type non-Euclidean ADMM for multi-block linearly constrained nonconvex programs
- Every critical point of an L0 composite minimization problem is a local minimizer
- Efficient and Robust Recovery of Sparse Signal and Image Using Generalized Nonconvex Regularization