On the convergence of the direct extension of ADMM for three-block separable convex minimization models with one strongly convex function

The alternating direction method of multipliers (ADMM) is a benchmark for solving a two-block linearly constrained convex minimization model whose objective function is the sum of two functions without coupled variables. Meanwhile, it is known that the convergence is not guaranteed if the ADMM is directly extended to a multiple-block convex minimization model whose objective function has more than two functions. Recently, some authors have actively studied the strong convexity condition on the objective function to sufficiently ensure the convergence of the direct extension of ADMM or the resulting convergence when the original scheme is appropriately twisted. We focus on the three-block case of such a model whose objective function is the sum of three functions, and discuss the convergence of the direct extension of ADMM. We show that when one function in the objective is strongly convex, the penalty parameter and the operators in the linear equality constraint are appropriately restricted, it is sufficient to guarantee the convergence of the direct extension of ADMM. We further estimate the worst-case convergence rate measured by the iteration complexity in both the ergodic and nonergodic senses, and derive the globally linear convergence in asymptotical sense under some additional conditions.

[1]  M. Hestenes Multiplier and gradient methods , 1969 .

[2]  Wotao Yin,et al.  Parallel Multi-Block ADMM with o(1 / k) Convergence , 2013, Journal of Scientific Computing.

[3]  R. Rockafellar Monotone Operators and the Proximal Point Algorithm , 1976 .

[4]  Shiqian Ma,et al.  On the Global Linear Convergence of the ADMM with MultiBlock Variables , 2014, SIAM J. Optim..

[5]  Xiaowei Zhou,et al.  Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  M. J. D. Powell,et al.  A method for nonlinear constraints in minimization problems , 1969 .

[7]  S. M. Robinson Some continuity properties of polyhedral multifunctions , 1981 .

[8]  John Wright,et al.  RASL: Robust Alignment by Sparse and Low-Rank Decomposition for Linearly Correlated Images , 2012, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  J. Moreau Proximité et dualité dans un espace hilbertien , 1965 .

[10]  Wei Hong Yang,et al.  Linear Convergence of the Alternating Direction Method of Multipliers for a Class of Convex Optimization Problems , 2016, SIAM J. Numer. Anal..

[11]  Tianyi Lin,et al.  On the Convergence Rate of Multi-Block ADMM , 2014, 1408.4265.

[12]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[13]  Bingsheng He,et al.  Linearized Alternating Direction Method with Gaussian Back Substitution for Separable Convex Programming , 2011 .

[14]  Daniel Boley,et al.  Local Linear Convergence of the Alternating Direction Method of Multipliers on Quadratic or Linear Programs , 2013, SIAM J. Optim..

[15]  Xiaoming Yuan,et al.  Recovering Low-Rank and Sparse Components of Matrices from Incomplete and Noisy Observations , 2011, SIAM J. Optim..

[16]  Xiaoming Yuan,et al.  A splitting method for separable convex programming , 2015 .

[17]  Xiaoming Yuan,et al.  A Note on the Alternating Direction Method of Multipliers , 2012, J. Optim. Theory Appl..

[18]  Caihua Chen,et al.  On the Convergence Analysis of the Alternating Direction Method of Multipliers with Three Blocks , 2013 .

[19]  Zhi-Quan Luo,et al.  On the linear convergence of the alternating direction method of multipliers , 2012, Mathematical Programming.

[20]  Roland Glowinski,et al.  On Alternating Direction Methods of Multipliers: A Historical Perspective , 2014, Modeling, Simulation and Optimization for Science and Technology.

[21]  Xiaoming Yuan,et al.  Local Linear Convergence of the Alternating Direction Method of Multipliers for Quadratic Programs , 2013, SIAM J. Numer. Anal..

[22]  Antonin Chambolle,et al.  A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging , 2011, Journal of Mathematical Imaging and Vision.

[23]  Xi Yin Zheng,et al.  Metric Subregularity of Piecewise Linear Multifunctions and Applications to Piecewise Linear Multiobjective Optimization , 2014, SIAM J. Optim..

[24]  Wotao Yin,et al.  On the Global and Linear Convergence of the Generalized Alternating Direction Method of Multipliers , 2016, J. Sci. Comput..

[25]  Xiaodong Li,et al.  Stable Principal Component Pursuit , 2010, 2010 IEEE International Symposium on Information Theory.

[26]  A. Willsky,et al.  Latent variable graphical model selection via convex optimization , 2010, 1008.1290.

[27]  R. Glowinski,et al.  Numerical Methods for Nonlinear Variational Problems , 1985 .

[28]  Bingsheng He,et al.  The direct extension of ADMM for multi-block convex minimization problems is not necessarily convergent , 2014, Mathematical Programming.

[29]  G. McLachlan Discriminant Analysis and Statistical Pattern Recognition , 1992 .

[30]  Xiaoming Yuan,et al.  An augmented Lagrangian based parallel splitting method for separable convex minimization with applications to image processing , 2014, Math. Comput..

[31]  Su-In Lee,et al.  Node-based learning of multiple Gaussian graphical models , 2013, J. Mach. Learn. Res..

[32]  Xiaoming Yuan,et al.  Convergence rate and iteration complexity on the alternating direction method of multipliers with a substitution procedure for separable convex programming , 2012 .

[33]  Xiaoming Yuan,et al.  A Generalized Proximal Point Algorithm and Its Convergence Rate , 2014, SIAM J. Optim..

[34]  Kim-Chuan Toh,et al.  A Convergent 3-Block Semi-Proximal ADMM for Convex Minimization Problems with One Strongly Convex Block , 2014, Asia Pac. J. Oper. Res..