Abstract
In this paper, we obtain global pointwise and ergodic convergence rates for a variable metric proximal alternating direction method of multipliers for solving linearly constrained convex optimization problems. We first propose and study nonasymptotic convergence rates of a variable metric hybrid proximal extragradient framework for solving monotone inclusions. Then, the convergence rates for the former method are obtained essentially by showing that it falls within the latter framework. To the best of our knowledge, this is the first time that global pointwise (resp. pointwise and ergodic) convergence rates are obtained for the variable metric proximal alternating direction method of multipliers (resp. variable metric hybrid proximal extragradient framework).
Similar content being viewed by others
References
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), 1–122 (2011)
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)
Glowinski, R., Marroco, A.: Sur l’approximation, par éléments finis d’ordre un, et la résolution, par penalisation-dualité, d’une classe de problèmes de Dirichlet non linéaires (1975)
Attouch, H., Soueycatt, M.: Augmented Lagrangian and proximal alternating direction methods of multipliers in Hilbert spaces. Applications to games, PDE’s and control. Pac. J. Optim. 5(1), 17–37 (2008)
He, B., Liu, H., Wang, Z., Yuan, X.: A strictly contractive peaceman-rachford splitting method for convex programming. SIAM J. Optim. 24(3), 1011–1040 (2014)
Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40(1), 120–145 (2011)
Davis, D., Yin, W.: Convergence rate analysis of several splitting schemes. In: Glowinski, R., Osher, S., Yin, W. (eds.) Splitting Methods in Communication, Imaging, Science and Engineering, pp. 115–163. Springer, New York (2016)
Deng, W., Yin, W.: On the global and linear convergence of the generalized alternating direction method of multipliers. J. Sci. Comput. 66(3), 889–916 (2016)
Eckstein, J.: Some saddle-function splitting methods for convex programming. Optim. Method Softw. 4(1), 75–83 (1994)
Fang, E.X., Bingsheng, H., Liu, H., Xiaoming, Y.: Generalized alternating direction method of multipliers: new theoretical insights and applications. Math. Prog. Comput. 7(2), 149–187 (2015)
Fazel, M., Pong, T.K., Sun, D., Tseng, P.: Hankel matrix rank minimization with applications to system identification and realization. SIAM J. Matrix Anal. Appl. 34(3), 946–977 (2013)
Gonçalves, M.L.N., Melo, J.G., Monteiro, R.D.C.: Improved pointwise iteration-complexity of a regularized ADMM and of a regularized non-euclidean HPE framework. SIAM J. Optim. 27(1), 379–407 (2017)
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. 54(3), 1535–1556 (2016)
He, B., Liao, L.Z., Han, D., Yang, H.: A new inexact alternating directions method for monotone variational inequalities. Math. Program. 92(1, Ser. A), 103–118 (2002)
He, B., Yuan, X.: On the \(\cal{O}(1/n)\) convergence rate of the Douglas–Rachford alternating direction method. SIAM J. Numer. Anal. 50(2), 700–709 (2012)
Lin, T., Ma, S., Zhang, S.: An extragradient-based alternating direction method for convex minimization. Found. Comput. Math. 17(1), 35–59 (2015)
Ouyang, Y., Chen, Y., Lan, G., Pasiliao Jr., E.: An accelerated linearized alternating direction method of multipliers. SIAM J. Imaging Sci. 8(1), 644–681 (2015)
Shefi, R., Teboulle, M.: Rate of convergence analysis of decomposition methods based on the proximal method of multipliers for convex minimization. SIAM J. Optim. 24(1), 269–297 (2014)
BoŢ, R.I., Csetnek, E.R.: ADMM for monotone operators: convergence analysis and rates. https://arxiv.org/pdf/1705.01913.pdf
Monteiro, R.D.C., Svaiter, B.F.: Iteration-complexity of block-decomposition algorithms and the alternating direction method of multipliers. SIAM J. Optim. 23(1), 475–507 (2013)
Solodov, M.V., Svaiter, B.F.: A hybrid approximate extragradient-proximal point algorithm using the enlargement of a maximal monotone operator. Set Valued Anal. 7(4), 323–345 (1999)
Zhang, X., Burger, M., Bresson, X., Osher, S.: Bregmanized nonlocal regularization for deconvolution and sparse reconstruction. SIAM J. Imaging Sci. 3(3), 253–276 (2010)
He, B., Yuan, X.: On non-ergodic convergence rate of Douglas–Rachford alternating direction method of multipliers. Numer. Math. 130(3), 567–577 (2015)
Cui, Y., Li, X., Sun, D., Toh, K.C.: On the convergence properties of a majorized ADMM for linearly constrained convex optimization problems with coupled objective functions. J. Optim. Theory Appl. 169(3), 1013–1041 (2016)
Gonçalves, M.L.N., Melo, J.G., Monteiro, R.D.C.: Extending the ergodic convergence rate of the proximal ADMM. https://arxiv.org/pdf/1611.02903.pdf
Shen, L., Pan, S.: Weighted iteration complexity of the sPADMM on the KKT residuals for convex composite optimization. https://arxiv.org/pdf/1611.03167.pdf
He, B., Yang, H.: Some convergence properties of a method of multipliers for linearly constrained monotone variational inequalities. Oper. Res. Lett. 23(3–5), 151–161 (1998)
He, B.S., Yang, H., Wang, L.: Alternating direction method with self-adaptive penalty parameters for monotone variational inequalities. J. Optim. Theory Appl. 106(2), 337–356 (2000)
Solodov, M.V.: A class of decomposition methods for convex optimization and monotone variational inclusions via the hybrid inexact proximal point framework. Optim. Method Softw. 19(5), 557–575 (2004)
Lotito, P.A., Parente, L.A., Solodov, M.V.: A class of variable metric decomposition methods for monotone variational inclusions. J. Convex Anal. 16(3&4), 857–880 (2009)
Banert, S., BoŢ, R.I., Csetnek, E.R.: Fixing and extending some recent results on the ADMM algorithm. https://arxiv.org/pdf/1612.05057.pdf
Monteiro, R.D.C., Svaiter, B.F.: On the complexity of the hybrid proximal extragradient method for the iterates and the ergodic mean. SIAM J. Optim. 20(6), 2755–2787 (2010)
He, Y., Monteiro, R.D.C.: An accelerated HPE-type algorithm for a class of composite convex-concave saddle-point problems. SIAM J. Optim. 26(1), 29–56 (2016)
Marques Alves, M., Monteiro, R.D.C., Svaiter, B.F.: Regularized HPE-type methods for solving monotone inclusions with improved pointwise iteration-complexity bounds. SIAM J. Optim. 26(4), 2730–2743 (2016)
Monteiro, R.D.C., Svaiter, B.F.: Complexity of variants of Tseng’s modified F-B splitting and Korpelevich’s methods for hemivariational inequalities with applications to saddle-point and convex optimization problems. SIAM J. Optim. 21(4), 1688–1720 (2011)
Parente, L.A., Lotito, P.A., Solodov, M.V.: A class of inexact variable metric proximal point algorithms. SIAM J. Optim. 19(1), 240–260 (2008)
Rockafellar, R.T.: On the maximal monotonicity of subdifferential mappings. Pac. J. Math. 33, 209–216 (1970)
Burachik, R.S., Sagastizábal, C.A., Svaiter, B.F.: \(\epsilon \)-enlargements of maximal monotone operators: theory and applications. In: Reformulation: Nonsmooth, Piecewise Smooth, Semismooth and Smoothing Methods (Lausanne, 1997), Appl. Optim., vol. 22, pp. 25–43. Kluwer Acad. Publ., Dordrecht (1999)
Burachik, R.S., Iusem, A.N., Svaiter, B.F.: Enlargement of monotone operators with applications to variational inequalities. Set Valued Anal. 5(2), 159–180 (1997)
Rockafellar, R.T.: Convex Analysis. Princeton University Press, Princeton (1970)
Acknowledgements
The work of these authors was supported in part by CNPq Grants 406250/2013-8, 444134/2014-0, 309370/2014-0 and 406975/2016-7. We thank the reviewers for their careful reading and comments.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Hedy Attouch.
Appendix A Proofs of Theorems 3.1 and 3.2
Appendix A Proofs of Theorems 3.1 and 3.2
We start by presenting the following two Lemmas.
Lemma A.1
For any \(z^*,z,z_+,\tilde{z}\in \mathscr {Z}\) and \(M\in \mathscr {M}^{\mathscr {Z}}_{+}\), we have
Proof
Direct calculations yield
\(\square \)
Lemma A.2
Let \(\{z_k\}\), \(\{M_k\}\), \(\{\tilde{z}_k\}\) and \(\{\eta _k\}\) be generated by the variable metric HPE framework. For every \(k \ge 1\) and \(z^* \in T^{-1}(0):\)
-
(a)
we have
$$\begin{aligned} \Vert z^*-z_{k}\Vert _{\mathscr {Z},M_k}^2\le \Vert z^*-z_{k-1}\Vert _{\mathscr {Z},M_k}^2 +\eta _{k-1}-\eta _{k}-(1 - \sigma ) \Vert z_{k-1}-\tilde{z}_k\Vert _{\mathscr {Z},M_k}^2; \end{aligned}$$ -
(b)
we have
$$\begin{aligned}&\Vert z^*-z_{k}\Vert _{\mathscr {Z},M_k}^2+\eta _k+(1-\sigma ) \displaystyle \sum _{i=1}^k\Vert z_{i-1}-\tilde{z}_i\Vert _{\mathscr {Z},M_i}^2 \\&\quad \le C_P (\Vert z^*-z_{0}\Vert _{\mathscr {Z},M_0}^2 + \eta _{0})\,, \end{aligned}$$where \(C_P\) and \(M_0\) are as in (11) and condition C1, respectively.
Proof
-
(a)
From Lemma A.1 with \((z,z_+,\tilde{z})=(z_{k-1},z_k,\tilde{z}_k)\) and \(M=M_k\), (12) and (13), we obtain
$$\begin{aligned}&\Vert z^*-z_{k-1}\Vert _{\mathscr {Z},M_k}^2 - \Vert z^*-z_{k}\Vert _{\mathscr {Z},M_k}^2 +\eta _{k-1}\\&\quad \ge (1-\sigma ) \Vert z_{k-1}-\tilde{z}_k\Vert _{\mathscr {Z},M_k}^2+\eta _k + 2\langle \tilde{z}_k-z^*, r_k\rangle . \end{aligned}$$Hence, (a) follows from the above inequality, the fact that \(0 \in T(z^*)\) and \(r_k \in T(\tilde{z}_k)\) (see (12)), and the monotonicity of T.
-
(b)
Using (a), (3) and condition C1, we find
$$\begin{aligned}&\Vert z^*-z_{k}\Vert _{\mathscr {Z},M_k}^2 \le (1+c_{k-1})\Vert z^*-z_{k-1}\Vert _{\mathscr {Z},\,M_{k-1}}^2\\&\quad +\,\eta _{k-1}-\eta _{k}-(1 - \sigma ) \Vert z_{k-1}-\tilde{z}_k\Vert _{\mathscr {Z},\,M_k}^2. \end{aligned}$$Thus, the result follows by applying the above inequality recursively and by using (11).\(\square \)
We are now ready to prove Theorem 3.1.
Proof of Theorem 3.1:
First, note that the desired inclusion holds due to (12). Now, using (2) and (13), we obtain, respectively,
Combining the above inequalities, we find
which in turn, combined with Lemma A.2(b), yields
for all \(z^*\in T^{-1}(0)\). Now, from (11), we obtain \(M_i\preceq C_P M_0\) for every \(i\ge 1\). Thus, it follows from (12) and Proposition 2.1 that
which, combined with the fact that \(\sum _{i=1}^k\,t_i\ge k\min _{i=1,\dots , k} \{t_i\}\) and the definition in (14), proves (15). \(\square \)
Before proceeding to the proof of the ergodic convergence of the variable metric HPE framework, let us first present an auxiliary result.
Proposition A.1
Let \(\{z_k\}\), \(\{M_k\}\) and \(\{\eta _k\}\) be generated by the variable metric HPE framework and consider \(\{\tilde{z}_k^a\}\) and \(\{\varepsilon _k^a\}\) as in (18). Then, for every \(k\ge 1\),
where \(\{c_k\}\) is given in condition C1.
Proof
Using Lemma A.1 with \((z^*,z,z_+,\tilde{z})=(\tilde{z}^a_{k},z_{i-1},z_i,\tilde{z}_i)\) and \(M=M_i\), (12) and (13), we find, for every \(i=1,\dots ,k\),
where the second inequality is due to the fact that \(1-\sigma \ge 0\). Hence, using condition C1 and simple calculations, we obtain
Summing up the last inequality from \(i=1\) to \(i=k\) and using the definition of \(\varepsilon _k^a\) in (18), we have
which clearly gives (69). \(\square \)
Proof of Theorem 3.2:
Note first that the desired inclusion and the first inequality in (20) follow from (12), (18) and Theorem 2.1(a). Take \(z^*\in T^{-1}(0)\). Now, let us prove the second inequality in (20), which will follow by bounding the term in the right-hand side of (69). Note that, using the convexity of \(\Vert \cdot \Vert _{M_{i-1}}^2\), inequality (2) and (18), we find
From (11), we have \(M_{i-1}\preceq C_PM_j\) for all \(j=1,\ldots , k\). Hence, using Proposition 2.1, inequality (13), Lemma A.2(b) and (14), we find
On the other hand, using (2), \(M_{i-1}\preceq C_P M_j\) for all \(j=1,\ldots , k\), Proposition 2.1, Lemma A.2(b) and (14), we obtain
It follows from inequalities (70)–(72) and the fact that \(k\ge 1\) that
which, combined with Proposition A.1 and the first condition in (10), yields
Therefore, the second inequality in (20) now follows from definition of \(\widehat{\mathscr {E}}\) and simple calculations.
To finish the proof of the theorem, it remains to prove (19). Assume first that \(k\ge 2\). Using (18) and simple calculations, we have
Since \(M_k\preceq C_P M_0\) and \(M_1\preceq C_P M_0\) (see (11)), we obtain from Proposition 2.1 that
Next step is to estimate the general term in the summation in (73). To do this, first note that using condition C1, we find
and so
It follows from the last inequality in (76) and (11) that \(L_i\preceq c_i(2+c_i)M_i\) and \(M_i\preceq C_P M_0\). Hence, we have
Again, using the facts that \(M_{i+1}\preceq C_P M_0\) and \(M_{i+1}\preceq (1+c_i)M_i\) (see (11)), and Proposition 2.1, we obtain
Hence, using (11) and (77)–(79), we find
Finally, using the definition of \(d_0\) in (14), (73)–(75), (80) and Lemma A.2(b), we conclude that
which gives (19) for the case \(k\ge 2\). Note now that by (11), we have \(M_1\preceq C_PM_0\) and so, using the second identity in (18) with \(k=1\), Proposition 2.1, Lemma A.2(b) and (14), we find
which, in turn, gives (19) for \(k=1\). \(\square \)
Rights and permissions
About this article
Cite this article
Gonçalves, M.L.N., Alves, M.M. & Melo, J.G. Pointwise and Ergodic Convergence Rates of a Variable Metric Proximal Alternating Direction Method of Multipliers. J Optim Theory Appl 177, 448–478 (2018). https://doi.org/10.1007/s10957-018-1232-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10957-018-1232-6
Keywords
- Alternating direction method of multipliers
- Variable metric
- Pointwise and ergodic convergence rates
- Hybrid proximal extragradient method
- Convex program