Abstract
In this paper, we consider a proximal linearized alternating direction method of multipliers, or PL-ADMM, for solving linearly constrained nonconvex and possibly nonsmooth optimization problems. The algorithm is generalized by using variable metric proximal terms in the primal updates and an over-relaxation step in the multiplier update. Extended results based on the augmented Lagrangian including subgradient band, limiting continuity, descent and monotonicity properties are established. We prove that the PL-ADMM sequence is bounded. Under the powerful Kurdyka-Łojasiewicz inequality we show that the PL-ADMM sequence has a finite length thus converges, and we drive its convergence rates.
Similar content being viewed by others
References
Ames, B., Hong, M.: Alternating directions method of multipliers for \(\ell _1\)-penalized zero variance discriminant analysis and principal component analysis. Comput. Optim. Appl. 64, 725–754 (2016)
Attouch, H., Bolte, J.: On the convergence of the proximal algorithm for nonsmooth functions involving analytic features. Math. Program. 116, 5–16 (2009)
Attouch, H., Bolte, J., Redont, P., Soubeyran, A.: Proximal alternating minimization and projection methods for nonconvex problems: an approach based on the Kurdyka-Łojasiewicz inequality. Math. Oper. Res. 35, 438–457 (2010)
Attouch, H., Bolte, J., Svaiter, B.: Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized gauss-seidel methods. Math. Program. Ser. A 137, 91–129 (2013)
Bai, J., Hager, W. W., Zhang, H.: An inexact accelerated stochastic ADMM for separable convex optimization, arXiv preprint arXiv:2010.12765, (2020)
Bai, J., Han, D., Sun, H., Zhang, H.: Convergence on a symmetric accelerated stochastic admm with larger stepsizes, arXiv preprint arXiv:2103.16154, (2021)
Bai, J., Li, J., Xu, F., Zhang, H.: Generalized symmetric ADMM for separable convex optimization. Comput. Optim. Appl. 70, 129–170 (2018)
Boley, D.: Local linear convergence of the alternating direction method of multipliers on quadratic or linear programs. SIAM J. Optim 23, 2183–2207 (2013)
Bolte, J., Daniilidis, A., Lewis, A.: The Łojasiewicz inequality for nonsmooth subanalytic functions with applications to subgradient dynamical systems. SIAM J. Optim 17, 1205–1223 (2006)
Bolte, J., Daniilidis, A., Ley, M., Mazet, L.: Characterizations of Łojasiewicz inequalities: Subgradientflows, talweg, convexity. Trans. Am. Math. Soc. 362, 3319–3363 (2010)
Bolte, J., Sabach, S., Teboulle, M.: Proximal alternating linearized minimization for nonconvex and nonsmooth problems. Math. Program. 146, 459–494 (2014)
Bolte, J., Daniilidis, A., Shiota, M.: Clarke subgradients of stratifiable functions. SIAM J. Optim. 18, 556–572 (2007)
Boţ, R., Nguyen, D.: The proximal alternating direction method of multipliers in the nonconvex setting: Convergence analysis and rates. Math. Oper. Res. 45, 682–712 (2020)
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., Han, D., Yuan, X.: The direct extension of ADMM for three-block separable convex minimization models is convergent when one function is strongly convex, http://www.optimization-online.org, 2013 (2015)
Chen, C., He, B., Yuan, X., Ye, Y.: The direct extension of ADMM for multi-block convex minimization problems is not necessarily convergent. Math. Program. 55, 57–79 (2016)
Chen, C., Shen, Y., You, Y.: On the convergence analysis of the alternating direction method of multipliers with three blocks. Abstr. Appl. Anal. 2015, 1–7 (2013)
Chen, Y., Hager, W.W., Yashtini, M., Ye, X., Zhang, H.: Bregman operator splitting with variable stepsize for Total Variation image reconstruction. Comput. Optim. Appl. 54, 317–342 (2013)
Cirik, A.C., Balasubramanya, N.M., Lampe, L.: Multi-user detection using ADMM-based compressive sensing for uplink grant-free noma. IEEE Wirel. Commun. Lett. 7, 46–49 (2017)
Dai, Y., Han, D., Yuan, X., Zhang, W.: A sequential updating scheme of Lagrange multiplier for separable convex programming. Math. Comput. 86, 315–343 (2017)
Davis, D., Yin, W.: A three-operator splitting scheme and its optimization applications. Set-Valued Var. Anal. 25, 829–858 (2017)
Deng, W., Lai, M., Peng, Z., Yin, W.: Parallel multi-block ADMM with \(o(1/k)\) convergence. J. Sci. Comput. 71, 712–736 (2017)
Deng, W., Yin, W.: On the global and linear convergence of the generalized alternating direction method of multipliers. J. Sci. Comput. 66, 889–916 (2015)
Dhar, S., Yi, C., Ramakrishnan, N., Shah, M.: ADMM based scalable machine learning on spark, In 2015 IEEE International Conference on Big Data (Big Data), IEEE, (2015), pp. 1174–1182
Douglas, J., Rachford, H.: On the numerical solution of the heat conduction problem in 2 and 3 space variables. Trans. Am. Math. Soc. 82, 421–439 (1956)
Eckstein, J., Bertsekas, D.: On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators. Math. Program. 55, 293–318 (1992)
Fan, J.: Comments on wavelets in statistics: a review by a antoniadis. J. Ital. Stat. Soc. 6, 131–138 (1997)
Forero, P.A., Cano, A., Giannakis, G.B.: Distributed clustering using wireless sensor networks. IEEE J. Sel. Topics Signal Process. 5, 707–724 (2011)
Frankel, P., Garrigos, G., Peypouquet, J.: Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates. J. Optim. Theory Appl. 165, 874–900 (2015)
Gabay, D., Mercier, B.: A dual algorithm for the solution of nonlinear variational problems via finite element approximations. Comput. Math. Appl. 2, 17–40 (1976)
Glowinski, R., Marroco, A.: Sur l’approximation, par éléments finis d’ordre un, et la résolution, par pénalisation-dualité d’une classe de problèmes de dirichlet non linéaires. ESAIM Math Modell Numer Anal Modélisation Mathématique et Analyse Numérique 9, 41–76 (1975)
Goldfarb, D., Ma, S.: Fast multiple-splitting algorithms for convex optimization. SIAM J. Optim. 22, 533–556 (2012)
Goldfarb, D., Ma, S., Scheinberg, K.: Fast alternating linearization methods for minimizing the sum of the two convex functions. Math. Program. 141, 349–382 (2013)
Goldstein, T., O’Donoghue, B., Setzer, S., Baraniuk, R.: Fast alternating direction optimization methods. SIAM. J. Imag. Sci. 7, 1588–1623 (2014)
Guo, K., Han, D., Wu, T.: Convergence of alternating direction method for minimizing sum of two nonconvex functions with linear constraints. Int. J. Comput. Math 94, 1653–1669 (2017)
Hager, W.W., Ngo, C., Yashtini, M., Zhang, H.: Alternating direction approximate Newton (ADAN) algorithm for ill-conditioned inverse problems with application to parallel MRI. J. Oper. Res. Soc. China 3, 139–162 (2015)
Hager, W.W., Yashtini, M., Zhang, H.: An \({O}(1/k)\) convergence rate for the variable stepsize Bregman operator splitting algorithm. SIAM J. Numer. Anal. 53, 1535–1556 (2016)
Han, D., Yuan, X.: A note on the alternating direction method of multipliers. J. Optim. Theory Appl. 155, 227–238 (2012)
He, B., Hou, L., Yuan, X.: On full Jacobian decomposition of the augmented lagrangian method for separable convex programming. SIAM J. Optim. 25, 2274–2312 (2015)
He, B., Tao, M., Xu, M., Yuan, X.: Alternating directions based contraction method for generally separable linearly constrained convex programming problem, http://www.optimization-online.org, (2010)
He, B., Tao, M., Yuan, X.: Alternating direction method with Gaussian back substitution for separable convex programming. SIAM J. Optim. 22, 313–340 (2012)
He, B., Tao, M., Yuan, X.: Convergence rate and iteration complexity on the alternating direction method of multipliers with a substitution procedure for separable convex programming. Math. Oper. Res. 42, 662–691 (2017)
He, B., Yuan, X.: On the O(1/n) convergence rate of the Douglas-Rachford alternating direction method. SIAM. J. Numer. Anal. 2, 700–709 (2012)
He, B., Yuan, X.: On non-ergodic convergence rate of the Douglas-Rachford alternating direction method of multipliers. Numerische Mathematik 130, 567–577 (2014)
Hong, M., Luo, Z.: On the linear convergence of the alternating direction method of multipliers. Math. Program. 162, 165–199 (2017)
Hong, M., Luo, Z., Razaviyayn, M.: Convergence analysis of alternating direction method of multipliers for a family of nonconvex problems. SIAM J. Optim. 26, 337–364 (2016)
Jiang, B., Lin, T., Ma, S., Zhang, S.: Structured nonconvex and nonsmooth optimization: algorithms and iteration complexity analysis. Comput. Optim. Appl. 72, 115–157 (2019)
Li, G., Pong, T.K.: Global convergence of splitting methods for nonconvex composite optimization. SIAM J. Optim. 25, 2434–2460 (2015)
Liégeois, R., Mishra, B., Zorzi, M., Sepulchre, R.: Sparse plus low-rank autoregressive identification in neuroimaging time series, In 2015 54th IEEE Conference on Decision and Control (CDC), IEEE, (2015), pp. 3965–3970
Lin, F., Fardad, M., Jovanovic, M.R.: Design of optimal sparse feedback gains via the alternating direction method of multipliers. IEEE Trans. Automat. Control 58, 2426–2431 (2013)
Lin, T., Ma, S., Zhang, S.: On the sublinear convergence rate of multi-block ADMM. J. Oper. Res. Soc. China 3, 251–274 (2015)
Lin, T., Ma, S., Zhang, S.: Global convergence of unmodified 3-block ADMM for a class of convex minimization problems. J. Sci. Comput. 76, 69–88 (2018)
Lions, P.L., Mercier, B.: Splitting algorithms for the sum of two nonlinear operators. SIAM J. Numer. Anal. 16, 964–979 (1979)
Liu, Q., Shen, X., Gu, Y.: Linearized ADMM for nonconvex nonsmooth optimization with convergence analysis. IEEE Access 7, 76131–76144 (2019)
Liu, Y., Shang, F., Liu, H., Kong, L., Licheng, J., Lin, Z.: Accelerated variance reduction stochastic ADMM for large-scale machine learning, IEEE Trans. Pattern Anal. Mach. Intell., (2020)
Lu, C.: A library of ADMM for sparse and low-rank optimization. Methodology 68, 49–67 (2006)
Melo, J.G., Monteiro, R.D.: Iteration complexity of a linearized proximal multiblock ADMM class for linearly constrained nonconvex optimization problems, http://www.optimization-online.org, (2017)
Peaceman, D., Rachford, H.: The numerical solution of parabolic elliptic differential equations. SIAM J. Appl. Math. 3, 28–41 (1955)
Rockafellar, R.T., Wets, R.: Variational analysis, vol. 317. Grundlehren der Mathematischen Wissenschaften, Springer, Berlin (1998)
Shen, Y., Wen, Z., Zhang, Y.: Augmented Lagrangian alternating direction method for matrix separation based on low-rank factorization. Optim. Methods Soft. 29, 239–263 (2014)
Themelis, A., Patrinos, P.: Douglas-Rachford splitting and ADMM for nonconvex optimization: tight convergence results. SIAM J. Optim. 30, 149–181 (2020)
Wang, F., Can, W., Xu, Z.: Convergence of multi-block Bregman ADMM for nonconvex composite problems. Sci. China Inf. Sci. 61, 12210:11-122101:12 (2018)
Wang, Y., Yin, W., Zeng, J.: Global convergence of ADMM in nonconvex nonsmooth optimization. J. Sci. Comput. 78, 29–63 (2019)
Wen, Z., Yang, C., Liu, X., Marchesini, S.: Alternating direction methods for classical and ptychographic phase retrieval. Invers. Probl. 28, 1–18 (2012)
Wu, C., Tai, X.-C.: Augmented Lagrangian method, dual methods, and split Bregman iteration for ROF, vectorial TV, and high order models. SIAM J. Imag. Sci. 3, 300–339 (2010)
Yang, J., Zhang, Y., Yin, W.: A fast alternating direction method for TVL1-L2 signal reconstruction from partial Fourier data. IEEE J. Sel. Topics Signal Process. 4, 288–297 (2010)
Yang, L., Pong, T., Chen, X.: Alternating direction method of multipliers for a class of nonconvex and nonsmooth problems with applications to background/foreground extraction. SIAM J. Imag. Sci. 10, 74–110 (2017)
Yang, Y., Sun, J., Li, H., Xu, Z.: ADMM-Net: A deep learning approach for compressive sensing MRI, arXiv preprint arXiv:1705.06869, (2017)
Yang, Y., Sun, J., Li, H., Xu, Z.: ADMM-CSNet: a deep learning approach for image compressive sensing. IEEE Trans. Pattern Anal. Mach. Intell. 42, 521–538 (2018)
Yashtini, M.: Multi-block nonconvex nonsmooth proximal ADMM: convergence and rates under Kurdyka-Łojasiewicz property. J. Optim. Theory Appl. 190, 966–998 (2021)
Yashtini, M., Hager, W. W., Chen, Y., Ye, X.: Partially parallel MR image reconstruction using sensitivity encoding, In 2012 IEEE International Conference on Image Processing, Orlando, (2012), IEEE, pp. 2077–2080
Yashtini, M., Kang, S.H.: Alternating direction method of multipliers for Euler’s elastica-based denoising, SSVM 2015. LNCS 9087, 690–701 (2015)
Yashtini, M., Kang, S.H.: A fast relaxed normal two split method and an effective weighted TV approach for Euler’s Elastica image inpainting. SIAM J. Imag. Sci. 9, 1552–1581 (2016)
Yashtini, M., Kang, S.H., Zhu, W.: Efficient alternating minimization methods for variational edge-weighted colorization models. Adv. Comput. Math. 45, 1735–1767 (2019)
Yuan, X., Zeng, S., Zhang, J.: Discerning the linear convergence of ADMM for structured convex optimization through the lens of variational analysis. J. Mach. Learn. Res. 21, 1–75 (2020)
Zhang, C.: Nearly unbiased variable selection under minimax concave penalty. Ann. Stat. 38, 894–942 (2010)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yashtini, M. Convergence and rate analysis of a proximal linearized ADMM for nonconvex nonsmooth optimization. J Glob Optim 84, 913–939 (2022). https://doi.org/10.1007/s10898-022-01174-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10898-022-01174-8