Abstract
In this paper, we present a convergence rate analysis for the inexact Krasnosel’skiĭ–Mann iteration built from non-expansive operators. The presented results include two main parts: we first establish the global pointwise and ergodic iteration-complexity bounds; then, under a metric sub-regularity assumption, we establish a local linear convergence for the distance of the iterates to the set of fixed points. The obtained results can be applied to analyze the convergence rate of various monotone operator splitting methods in the literature, including the Forward–Backward splitting, the Generalized Forward–Backward, the Douglas–Rachford splitting, alternating direction method of multipliers and Primal–Dual splitting methods. For these methods, we also develop easily verifiable termination criteria for finding an approximate solution, which can be seen as a generalization of the termination criterion for the classical gradient descent method. We finally develop a parallel analysis for the non-stationary Krasnosel’skiĭ–Mann iteration.
Similar content being viewed by others
Notes
In fact, in many cases the fixed-point operator T is even \(\alpha \)-averaged, see Definition 1.
The authors consider the case where \(\mathcal {H}\) is any normed space.
One may observe that \(\gamma \) can be modified locally, once the iterates enter the appropriate neighbourhood, to get the usual optimal linear rate of gradient descent with a strongly convex objective [57]. But this is not our aim here.
Let \(\left( x_k,v_k\right) \in \text {gra}A\) be a sequence generated by an iterative method for solving the monotone inclusion problem \(0 \in A x\), then the non-uniform iteration-complexity bound means that for every \(k\in \mathbb {N}\), there exists a \(j\le k\) such that \(\Vert v_j\Vert =O(1/\sqrt{k})\).
References
Aragòn, F.J., Geoffroy, M.H.: Characterization of metric regularity of subdifferentials. J. Convex Anal. 15(2), 365–380 (2008)
Baillon, J.B.: Un théoreme de type ergodique pour les contractions non linéaires dans un espace de Hilbert. C.R. Acad. Sci. Paris Sér. AB 280, 1511–1514 (1975)
Baillon, J.B., Bruck, R.E.: The rate of asymptotic regularity is \({O}(1/\sqrt{n})\). Lect. Notes Pure Appl. Math. 178, 51–81 (1996)
Baillon, J.B., Haddad, G.: Quelques propriétés des opérateurs angle-bornés etn-cycliquement monotones. Israel J. Math. 26(2), 137–150 (1977)
Bauschke, H.H., Bello Cruz, J.Y., Nghia, T.A., Phan, H.M., Wang, X.: Optimal rates of convergence of matrices with applications (2014). arXiv:1407.0671
Bauschke, H.H., Combettes, P.L.: Convex Analysis and Monotone Operator Theory in Hilbert Spaces. Springer, New York (2011)
Bauschke, H.H., Luke, D.R., Phan, H.M., Wang, X.: Restricted normal cones and the method of alternating projections: theory. Set-Valued Var. Anal. 21(3), 431–473 (2013)
Bauschke, H.H., Noll, D., Phan, H.M.: Linear and strong convergence of algorithms involving averaged nonexpansive operators. J. Math. Anal. Appl. 421(1), 1–20 (2015)
Borwein, J.M., Sims, B.: The Douglas–Rachford algorithm in the absence of convexity. In: Fixed-Point Algorithms for Inverse Problems in Science and Engineering. Springer, pp. 93–109 (2011)
Brézis, H., Lions, P.L.: Produits infinis de résolvantes. Israel J. Math. 29(4), 329–345 (1978)
Briceno-Arias, L.M.: Forward-Douglas–Rachford splitting and forward-partial inverse method for solving monotone inclusions. Optimization 64(5), 1239–1261 (2015)
Briceno-Arias, L.M., Combettes, P.L.: A monotone+ skew splitting model for composite monotone inclusions in duality. SIAM J. Optim. 21(4), 1230–1250 (2011)
Burachik, R.S., Scheimberg, S., Svaiter, B.F.: Robustness of the hybrid extragradient proximal-point algorithm. J. Optim. Theory Appl. 111(1), 117–136 (2001)
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)
Chen, G., Teboulle, M.: A proximal-based decomposition method for convex minimization problems. Math. Program. 64(1–3), 81–101 (1994)
Chen, P., Huang, J., Zhang, X.: A primal–dual fixed point algorithm for convex separable minimization with applications to image restoration. Inverse Prob. 29(2), 025011 (2013)
Combettes, P.L.: Quasi-Fejérian analysis of some optimization algorithms. Stud. Comput. Math. 8, 115–152 (2001)
Combettes, P.L.: Solving monotone inclusions via compositions of nonexpansive averaged operators. Optimization 53(5–6), 475–504 (2004)
Combettes, P.L., Pesquet, J.C.: Primal–dual splitting algorithm for solving inclusions with mixtures of composite, Lipschitzian, and parallel-sum type monotone operators. Set-Valued Var. Anal. 20(2), 307–330 (2012)
Combettes, P.L., Wajs, V.R.: Signal recovery by proximal Forward–Backward splitting. Multiscale Model. Simul. 4(4), 1168–1200 (2005)
Cominetti, R., Soto, J.A., Vaisman, J.: On the rate of convergence of Krasnoselski–Mann iterations and their connection with sums of Bernoullis. Israel J. Math. 199(2), 757–772 (2014)
Condat, L.: A primal–dual splitting method for convex optimization involving Lipschitzian, proximable and linear composite terms. J. Optim. Theory Appl. 158(2), 460–479 (2013)
Demanet, L., Zhang, X.: Eventual linear convergence of the Douglas–Rachford iteration for basis pursuit. Math. Comput. (2015). doi:10.1090/mcom/2965
Dontchev, A.L., Quincampoix, M., Zlateva, N.: Aubin criterion for metric regularity. J. Convex Anal. 13, 281–297 (2006)
Dontchev, A.L., Rockafellar, R.T.: Implicit Functions and Solution Mappings: A View from Variational Analysis. Springer, New York (2009)
Douglas, J., Rachford, H.H.: On the numerical solution of heat conduction problems in two and three space variables. Trans. Am. Math. Soc. 82(2), 421–439 (1956)
Eckstein, J., Bertsekas, D.P.: On the Douglas–Rachford splitting method and the proximal point algorithm for maximal monotone operators. Math. Program. 55(1–3), 293–318 (1992)
Fortin, M., Glowinski, R.: Augmented Lagrangian Methods: Applications to the Numerical Solution of Boundary-Value Problems. Elsevier, Amsterdam (2000)
Gabay, D.: Chapter IX: applications of the method of multipliers to variational inequalities. Stud. Math. Appl. 15, 299–331 (1983)
Gabay, D., Mercier, B.: A dual algorithm for the solution of nonlinear variational problems via finite element approximation. Comput. Math. Appl. 2(1), 17–40 (1976)
Glowinski, R., Le Tallec, P.: Augmented Lagrangian and Operator-Splitting Methods in Nonlinear Mechanics, vol. 9. SIAM, Philadelphia (1989)
He, B., Yuan, X.: On non-ergodic convergence rate of Douglas–Rachford alternating direction method of multipliers. Numer. Math. 130(3), 567–577 (2012)
He, B., Yuan, X.: On convergence rate of the Douglas–Rachford operator splitting method. Math. Program. (2014). doi:10.1007/s10107-014-0805-x
Hesse, R., Luke, D.R.: Nonconvex notions of regularity and convergence of fundamental algorithms for feasibility problems. SIAM J. Optim. 23(4), 2397–2419 (2013)
Krasnosel’skii, M.A.: Two remarks on the method of successive approximations. Uspekhi Matematicheskikh Nauk 10(1), 123–127 (1955)
Lemaire, B.: Stability of the iteration method for non expansive mappings. Serdica Math. J. 22(3), 331p–340p (1996)
Lemaire, B.: Which fixed point does the iteration method select? In: Recent Advances in Optimization. Springer, pp. 154–167 (1997)
Leventhal, D.: Metric subregularity and the proximal point method. J. Math. Anal. Appl. 360(2), 681–688 (2009)
Lewis, A., Luke, D., Malick, J.: Local linear convergence for alternating and averaged nonconvex projections. Found. Comput. Math. 9(4), 485–513 (2009)
Li, G., Mordukhovich, B.S.: Hölder metric subregularity with applications to proximal point method. SIAM J. Optim. 22(4), 1655–1684 (2012)
Liang, J., Fadili, M.J., Peyré, G.: Local linear convergence of Forward–Backward under partial smoothness. In: Advances in Neural Information Processing Systems (NIPS), pp. 1970–1978 (2014)
Liang, J., Fadili, M.J., Peyré, G., Luke, R.: Activity identification and local linear convergence of Douglas–Rachford/ADMM under partial smoothness. In: SSVM 2015—International Conference on Scale Space and Variational Methods in Computer Vision (2015)
Lions, P.L., Mercier, B.: Splitting algorithms for the sum of two nonlinear operators. SIAM J. Numer. Anal. 16(6), 964–979 (1979)
Mann, W.R.: Mean value methods in iteration. Proc. Am. Math. Soc. 4(3), 506–510 (1953)
Martinet, B.: Brève communication. régularisation d’inéquations variationnelles par approximations successives. Revue française d’informatique et de rechercheopérationnelle, série rouge4(3), 154–158 (1970)
Mercier, B.: Topics in finite element solution of elliptic problems. In: Lectures on Mathematics, vol. 63 (1979)
Minty, G.J.: Monotone (nonlinear) operators in Hilbert space. Duke Math. J. 29(3), 341–346 (1962)
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)
Moreau, J.J.: Décomposition orthogonale d’un espace Hilbertien selon deux cônes mutuellement polaires. C.R. Acad. Sci. Paris 255, 238–240 (1962)
Moreau, J.J.: Proximité et dualité dans un espace Hilbertien. Bull. Soc. Math. France 93, 273–299 (1965)
Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course, vol. 87. Springer, New York (2004)
Ogura, N., Yamada, I.: Non-strictly convex minimization over the fixed point set of an asymptotically shrinking nonexpansive mapping. Numer. Funct. Anal. Optim. 23(1–2), 113–137 (2002)
Opial, Z.: Weak convergence of the sequence of successive approximations for nonexpansive mappings. Bull. Am. Math. Soc. 73(4), 591–597 (1967)
Passty, G.B.: Ergodic convergence to a zero of the sum of monotone operators in Hilbert space. J. Math. Anal. Appl. 72(2), 383–390 (1979)
Peaceman, D.W., Rachford Jr, H.H.: The numerical solution of parabolic and elliptic differential equations. J. Soc. Ind. Appl. Math. 3(1), 28–41 (1955)
Phan, H.M.: Linear convergence of the Douglas–Rachford method for two closed sets. Technical Report arXiv:1401.6509v1 (2014)
Polyak, B.T.: Introduction to Optimization. Optimization Software, New York (1987)
Raguet, H., Fadili, J., Peyré, G.: A generalized Forward–Backward splitting. SIAM J. Imaging Sci. 6(3), 1199–1226 (2013)
Reich, S.: Weak convergence theorems for nonexpansive mappings in Banach spaces. J. Math. Anal. Appl. 67, 274–276 (1979)
Rockafellar, R.T.: Monotone operators and the proximal point algorithm. SIAM J. Control Optim. 14(5), 877–898 (1976)
Solodov, M.V.: A class of decomposition methods for convex optimization and monotone variational inclusions via the hybrid inexact proximal point framework. Optim. Methods Softw. 19(5), 557–575 (2004)
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)
Svaiter, B.F.: A class of Fejer convergent algorithms, approximate resolvents and the hybrid proximal-extragradient method. J. Optim. Theory Appl. 162(1), 133–153 (2014)
Tseng, P.: Alternating projection-proximal methods for convex programming and variational inequalities. SIAM J. Optim. 7(4), 951–965 (1997)
Vũ, B.C.: A splitting algorithm for dual monotone inclusions involving cocoercive operators. Adv. Comput. Math. 38(3), 667–681 (2013)
Acknowledgments
This work has been partly supported by the European Research Council (ERC project SIGMA-Vision). J. Fadili is partly supported by Institut Universitaire de France. We would like to thank Yuchao Tang for pointing reference [52] to us.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liang, J., Fadili, J. & Peyré, G. Convergence rates with inexact non-expansive operators. Math. Program. 159, 403–434 (2016). https://doi.org/10.1007/s10107-015-0964-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10107-015-0964-4
Keywords
- Krasnosel’skiĭ–Mann iteration
- Monotone inclusion
- Non-expansive operator
- Convergence rates
- Asymptotic regularity
- Convex optimization