Abstract
Recently, the alternating direction method of multipliers (ADMM) has found many efficient applications in various areas; and it has been shown that the convergence is not guaranteed when it is directly extended to the multiple-block case of separable convex minimization problems where there are m ≥ 3 functions without coupled variables in the objective. This fact has given great impetus to investigate various conditions on both the model and the algorithm’s parameter that can ensure the convergence of the direct extension of ADMM (abbreviated as “e-ADMM”). Despite some results under very strong conditions (e.g., at least (m − 1) functions should be strongly convex) that are applicable to the generic case with a general m, some others concentrate on the special case of m = 3 under the relatively milder condition that only one function is assumed to be strongly convex. We focus on extending the convergence analysis from the case of m = 3 to the more general case of m ≥ 3. That is, we show the convergence of e-ADMM for the case of m ≥ 3 with the assumption of only (m − 2) functions being strongly convex; and establish its convergence rates in different scenarios such as the worst-case convergence rates measured by iteration complexity and the globally linear convergence rate under stronger assumptions. Thus the convergence of e-ADMM for the general case of m ≥ 4 is proved; this result seems to be still unknown even though it is intuitive given the known result of the case of m = 3. Even for the special case of m = 3, our convergence results turn out to be more general than the existing results that are derived specifically for the case of m = 3.
Similar content being viewed by others
References
Ash, J.M., Berele, A., Catoiu, S.: Plausible and Genuine Extensions of L’Hospital’s Rule. Math. Mag. 85, 52–60 (2012)
Bhatia, R., Elsner, L., Krause, G.: Bounds for the Variation of the Roots of a Polynomial and the Eigenvalues of a Matrix. Linear Algebra Appl. 142, 195–209 (1990)
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach Learn. 3, 1–122 (2010)
Cai, X.J., Han, D.R., Yuan, X.M.: The direct extension of ADMM for three-block separable convex minimization models is convergent when one function is strongly convex. Comput. Optim. Appl. 66, 39–73 (2017)
Chen, C.H., Shen, Y., You, Y.F.: On the convergence analysis of the alternating direction method of multipliers with three blocks. Abstr. Appl. Anal., 2013, Article ID 183961, 7 pages
Chen, C.H., He, B.S., Ye, Y.Y., Yuan, X.M.: The direct extension of ADMM for multi-block convex minimization problems is not necessarily convergent. Math. Program., Ser. A 155, 57–79 (2016)
Davis, D., Yin, W.T.: A three-operator splitting scheme and its optimization applications, available at https://arxiv.org/pdf/1504.01032v1.pdf
Eckstein, J., Yao, W.: Understanding the convergence of the alternating direction method of multipliers: Theoretical and computational perspectives. Pacific. J. Optim. 11, 619–644 (2015)
Facchinei, F., Pang, J.-S.: Finite-Dimensional Variational Inequalities and Complementarity problems, Volume I, Springer Series in Operations Research, Springer-Verlag (2003)
Gabay, D.: Applications of the method of multipliers to variational inequalities. In: Fortin, M., Glowinski, R. (eds.) Augmented Lagrangian Methods: Applications to the Solution of Boundary-Valued Problems, pp 299–331. North-Holland Publishing Co., Amsterdam (1983)
Gabay, D., Mercier, B.: A dual algorithm for the solution of nonlinear variational problems via finite element approximation. Comput. Math. Appl. 2, 17–40 (1976)
Garling, D.J.H.: Inequalities: A Journey into Linear Analysis. Cambridge University, United Kindom (2007)
Glowinski, R., Marrocco, A.: Sur l’approximation paréléments finis d’ordre un et larésolution par pénalisation-dualité d’une classe de problèmes de Dirichlet non linéaires. Revue Fr. Autom. Inform. Rech. Opér., Anal Numér 2, 41–76 (1975)
Glowinski, R.: On alternating direction methods of multipliers: A historical perspective. In: Fitzgibbon, W., Kuznetsov, Y.A., Neittaanm ki, P., Pironneau, O. (eds.) Modeling, Simulation and Optimization for Science and Technology, pp 59–82. Springer, Netherlands (2014)
Han, D.R., Yuan, X.M.: A note on the alternating direction method of multipliers. J. Optim. Theory Appli. 155, 227–238 (2013)
He, B.S., Yuan, X.M.: On the O(1/n) convergence rate of Douglas-Rachford alternating direction method. SIAM J. Numer. Anal. 50, 700–709 (2012)
He, B.S., Yuan, X.M.: On nonergodic convergence rate of Douglas-Rachford alternating direction method of multipliers. Numer. Math. 130, 567–577 (2015)
Hong, M., Luo, Z.Q.: On the linear convergence of alternating direction method of multipliers. Math. Program. 162, 165–199 (2017)
Li, M., Sun, D.F., Toh, K.C.: A convergent 3-block semi-proximal ADMM for convex minimization problems with one strongly convex block. Asia Pac. J. Oper. Res. 32(1550024), 19 (2015)
Lin, T.Y., Ma, S.Q., Zhang, S.Z.: On the sublinear convergence rate of multi-block ADMM. J. Oper. Res. Soc. China 3, 251–274 (2015)
Lin, T.Y., Ma, S.Q., Zhang, S.Z.: On the global linear convergence of the ADMM with multi-block variables. SIAM J. Optim. 25, 1478–1497 (2015)
Peng, Y.G., Ganesh, A., Wright, J., Xu, W.L., Ma, Y.: Robust alignment by sparse and low-rank decomposition for linearly correlated images. IEEE Tran. Pattern Anal. Mach. Intel. 34, 2233–2246 (2012)
Rockafellar, R.T.: Convex Analysis. Princeton University Press, Princeton (1970)
Sun, D.F., Toh, K.C., Yang, L.Q.: A convergent 3-block semi-proximal alternating direction method of multipliers for conic programming with 4-type constraints. SIAM J. Optim. 25, 882–915 (2015)
Tao, M., Yuan, X.M.: Recovering low-rank and sparse components of matrices from incomplete and noisy observations. SIAM J. Optim. 21, 57–81 (2011)
Wang, X.F., Hong, M.Y., Chang, T.H., Razaviyayn, M., Luo, Z. Q.: Joint day-ahead power procurement and load scheduling using stochastic alternating direction method of multipliers. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp 7754–7758 (2014)
Zhou, X., Yang, C., Yu, W.: Moving object detection by detecting contiguous outliers in the Low-Rank representation. IEEE Trans. Pattern Anal. Mach. Intell. 35, 597–610 (2013)
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by: Karsten Urban
M. Tao: This author was supported by the Natural Science Foundation of China: NSFC-11301280 and the sponsorship of Jiangsu overseas research and training program for university prominent young and middle-aged teachers and presidents.
X. Yuan: This author was supported by the General Research Fund from Hong Kong Research Grants Council: 12313516.
Rights and permissions
About this article
Cite this article
Tao, M., Yuan, X. Convergence analysis of the direct extension of ADMM for multiple-block separable convex minimization. Adv Comput Math 44, 773–813 (2018). https://doi.org/10.1007/s10444-017-9560-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10444-017-9560-x
Keywords
- Convex programming
- Alternating direction method of multipliers
- Multiple-block separable models
- Convergence analysis