Abstract
The main goal of this paper is to develop uniformly optimal first-order methods for convex programming (CP). By uniform optimality we mean that the first-order methods themselves do not require the input of any problem parameters, but can still achieve the best possible iteration complexity bounds. By incorporating a multi-step acceleration scheme into the well-known bundle-level method, we develop an accelerated bundle-level method, and show that it can achieve the optimal complexity for solving a general class of black-box CP problems without requiring the input of any smoothness information, such as, whether the problem is smooth, nonsmooth or weakly smooth, as well as the specific values of Lipschitz constant and smoothness level. We then develop a more practical, restricted memory version of this method, namely the accelerated prox-level (APL) method. We investigate the generalization of the APL method for solving certain composite CP problems and an important class of saddle-point problems recently studied by Nesterov (Math Program 103:127–152, 2005). We present promising numerical results for these new bundle-level methods applied to solve certain classes of semidefinite programming and stochastic programming problems.
Similar content being viewed by others
References
Ahmed, S.: Smooth Minimization of Two-Stage Stochastic Linear Programs. Manuscript, Georgia Institute of Technology (2006)
Auslender, A., Teboulle, M.: Interior gradient and proximal methods for convex and conic optimization. SIAM J. Optim. 16, 697–725 (2006)
Becker, S., Bobin, J., Candès, E.: NESTA: A Fast and Accurate First-Order Method for Sparse Recovery. Manuscript, California Institute of Technology (2009)
Ben-Tal, A., Nemirovski, A.S.: Lectures on Modern Convex Optimization: Analysis, Algorithms. Engineering Applications. MPS-SIAM Series on Optimization. SIAM, Philadelphia (2000)
Ben-Tal, A., Nemirovski, A.S.: Non-euclidean restricted memory level method for large-scale convex optimization. Math. Program. 102, 407–456 (2005)
Chenny, E.W., Goldstein, A.A.: Newton’s methods for convex programming and tchebytcheff approximation. Numer. Math. 1, 253–268 (1959)
d’Aspremont, A., Banerjee, O., El Ghaoui, L.: First-order methods for sparse covariance selection. SIAM J. Matrix Anal. Appl. 30, 56–66 (2008)
Devolder, O., Glineur, F., Nesterov, Y.E.: First-Order Methods of Smooth Convex Optimization with Inexact Oracle. Manuscript, CORE, Université catholique de Louvain, Louvain-la-Neuve, Belgium (Dec 2010)
Ghadimi, S., Lan, G.: Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization, II: shrinking procedures and optimal algorithms. Technical report, SIAM J. Optim. (to appear) (2010)
Ghadimi, S., Lan, G.: Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization, I: a generic algorithmic framework. SIAM J. Optim. 22, 1469–1492 (2012)
Helmberg, C., Rendl, F.: A spectral bundle method for semidefinite programming. SIAM J. Optim. 10, 673–696 (2000)
Hoffman, A.: On approximate solutions of systems of linear inequalities. J. Res. Natl. Bureau Stand Sect. B Math. Sci. 49, 263–265 (1952)
Juditsky, A., Nemirovski, A.S., Tauvel, C.: Solving Variational Inequalities with Stochastic Mirror-Prox Algorithm. Manuscript, Georgia Institute of Technology, Atlanta, GA (2008)
Kelley, J.E.: The cutting plane method for solving convex programs. J. SIAM 8, 703–712 (1960)
Kiwiel, K.C.: An aggregate subgradient method for nonsmooth convex minimization. Math. Program. 27, 320–341 (1983)
Kiwiel, K.C.: Proximity control in bundle methods for convex nondifferentiable minimization. Math. Program. 46, 105–122 (1990)
Kiwiel, K.C.: Proximal level bundle method for convex nondifferentable optimization, saddle point problems and variational inequalities. Math. Program. Ser. B 69, 89–109 (1995)
Lan, G., Lu, Z., Monteiro, R.D.C.: Primal-dual first-order methods with \({\cal O}(1/\epsilon )\) iteration-complexity for cone programming. Math. Program. 126, 1–29 (2011)
Lan, G.: An optimal method for stochastic composite optimization. Math. Program. 133(1), 365–397 (2012)
Lan, G., Nemirovski, A.S., Shapiro, A.: Validation analysis of mirror descent stochastic approximation method. Math. Program. 134, 425–458 (2012)
Lemaréchal, C.: An extension of davidon methods to non-differentiable problems. Math. Program. Study 3, 95–109 (1975)
Lemaréchal, C., Nemirovski, A.S., Nesterov, Y.E.: New variants of bundle methods. Math. Program. 69, 111–148 (1995)
Lewis, A.S., Wright, S.J.: A Proximal Method for Composite Minimization. Manuscript, Cornell University, Ithaca, NY (2009)
Linderoth, J., Wright, S.: Decomposition algorithms for stochastic programming on a computational grid. Comput. Optim. Appl. 24, 207–250 (2003)
Linderoth, J., Shapiro, A., Wright, S.: The empirical behavior of sampling methods for stochastic programming. Ann. Oper. Res. 142, 215–241 (2006)
Lu, Z.: Smooth optimization approach for sparse covariance selection. SIAM J. Optim. 19, 1807–1827 (2009)
Mak, W.K., Morton, D.P., Wood, R.K.: Monte carlo bounding techniques for determining solution quality in stochastic programs. Oper. Res. Lett. 24, 47–56 (1999)
Mosek. The Mosek Optimization Toolbox for Matlab Manual. Version 6.0 (revision 93). http://www.mosek.com
Nemirovski, A.S., Yudin, D.: Problem Complexity and Method Efficiency in Optimization. Wiley-Interscience Series in Discrete Mathematics. Wiley, XV (1983)
Nemirovski, A.S.: Efficient Methods in Convex Programming. Lecture notes, Technion (1994)
Nemirovski, A.S.: Prox-method with rate of convergence \(o(1/t)\) for variational inequalities with lipschitz continuous monotone operators and smooth convex-concave saddle point problems. SIAM J. Optim. 15, 229–251 (2005)
Nemirovski, A.S., Juditsky, A., Lan, G., Shapiro, A.: Robust stochastic approximation approach to stochastic programming. SIAM J. Optim. 19, 1574–1609 (2009)
Nemirovskii, A.S., Nesterov, Y.E.: Optimal methods for smooth convex minimization. Zh. Vichisl. Mat. Fiz. 25, 356–369 (1985). (In Russian)
Nesterov, Y.E.: Efficient Methods in Nonlinear Programming. Radio i Sviaz, Moscow (1989)
Nesterov, Y.E.: Gradient methods for minimizing composite objective functions. Technical report, Center for Operations Research and Econometrics (CORE), Catholic University of Louvain, September (2007)
Nesterov, Y.E.: A method for unconstrained convex minimization problem with the rate of convergence \(O(1/k^2)\). Doklady AN SSSR 269, 543–547 (1983)
Nesterov, Y.E.: On an approach to the construction of optimal methods of minimization of smooth convex functions. Ekonomo. i. Mat. Metody 24, 509–517 (1988)
Nesterov, Y.E.: Introductory Lectures on Convex Optimization: A Basic Course. Kluwer, Massachusetts (2004)
Nesterov, Y.E.: Excessive gap technique in nonsmooth convex minimization. SIAM J. Optim. 16, 235–249 (2005)
Nesterov, Y.E.: Smooth minimization of nonsmooth functions. Math. Program. 103, 127–152 (2005)
Nesterov, Y.E.: Smoothing technique and its applications in semidefinite optimization. Math. Program. 110, 245–259 (2007)
Oliveira, W., Sagastizábal, C., Scheimberg, S.: Inexact bundle methods for two-stage stochastic programming. SIAM J. Optim. 21(2), 517–544 (2011)
Peña, J.: Nash equilibria computation via smoothing techniques. Optima 78, 12–13 (2008)
Richtárik, P.: Approximate level method for nonsmooth convex minimization. J. Optim. Theory Appl. 152(2), 334–350 (2012)
Ruszczyński, A.: Nonlinear Optimization, 1st edn. Princeton University Press, Princeton (2006)
Sagastizábal, C.: Nonsmooth Optimization: Thinking Outside of the Black Box. SIAG/OPT Views-and-News, pp. 1–9 (2011)
Sen, S., Doverspike, R.D., Cosares, S.: Network planning with random demand. Telecommun. Syst. 3, 11–30 (1994)
Tseng, P.: On Accelerated Proximal Gradient Methods for Convex-Concave Optimization. Manuscript, University of Washington, Seattle (May 2008)
Acknowledgments
The author is very grateful to the co-editor Professor Adrian Lewis, the associate editor and two anonymous referees for their very useful suggestions for improving the quality and exposition of the paper.
Author information
Authors and Affiliations
Corresponding author
Additional information
The paper is a combined version of the two manuscripts previously submitted to Mathematical Programming, namely: “Bundle-type methods uniformly optimal for smooth and nonsmooth convex optimization” and “Level methods uniformly optimal for composite and structured nonsmooth convex optimization”.
The author of this paper was partially supported by NSF grants CMMI-1000347 and DMS-1319050, ONR grant N00014-13-1-0036, and NSF CAREER Award CMMI-1254446.
Appendix
Appendix
In this section, we provide the proof of Lemma 8.
Let \(F\) and \(F_\eta \) be defined in (4.11) and (4.13), respectively. Also let us denote, for any \(\eta > 0\) and \(x \in X\),
where \({{\mathcal {D}}}_v\) and \({{\mathcal {L}}}_\eta \) are defined in (3.7) and (4.15), respectively. Clearly, in view of (1.2) and (4.16), \(\psi _x\) is a majorant of both \(F_\eta \) and \(f\). Also let us define
Clearly, by the first relation in (4.16), we have
Moreover, we can easily check that, for any \(z \in Z_x\),
where \(\nabla \psi _x(z) = \nabla F_\eta (x) + {{\mathcal {L}}}_\eta (z-x)\).
The following results provides the characterization of a subgradient direction of \(F\).
Lemma 9
Let \(x \in {\mathbb {R}}^n\) and \(p \in {\mathbb {R}}^n\) be given. Then, \(\exists z \in Z_x\) such that
where \(F'(x) \in \partial F(x)\).
Proof
Let us denote
and \(z_0 = x + t p\). Clearly, in view of (7.2), we have \(z_0 \in Z_x\). By convexity of \(F\) and (7.4), we have
which clearly implies the result.\(\square \)
We are now ready to prove Lemma 8.
Proof of Lemma 8
First note that by the convexity of \(F\), we have
Moreover, by Lemma 9, \(\exists z_0 \in Z_{x_0}\) and \(z_1 \in Z_{x_1}\) s.t.
where the last inequality and equality follow from (7.3) and (4.15), respectively. Combining the above two relations, we have
The result now follows by tending \(\eta \) to \(+\infty \) in the above relation.\(\square \)
Rights and permissions
About this article
Cite this article
Lan, G. Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization. Math. Program. 149, 1–45 (2015). https://doi.org/10.1007/s10107-013-0737-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10107-013-0737-x