On the ergodic convergence rates of a first-order primal–dual algorithm
- 1.6k Downloads
We revisit the proofs of convergence for a first order primal–dual algorithm for convex optimization which we have studied a few years ago. In particular, we prove rates of convergence for a more general version, with simpler proofs and more complete results. The new results can deal with explicit terms and nonlinear proximity operators in spaces with quite general norms.
KeywordsSaddle-point problems First order algorithms Primal–dual algorithms Convergence rates Ergodic convergence
Mathematics Subject Classification49M29 65K10 65Y20 90C25
This research is partially supported by the joint ANR/FWF Project Efficient Algorithms for Nonsmooth Optimization in Imaging (EANOI) FWF n. I1148/ANR-12-IS01-0003. A.C. would like to thank his colleague S. Gaiffas for stimulating discussions, as well as J. Fadili for very helpful discussions on nonlinear proximity operators. This work also benefited from the support of the “Gaspard Monge Program in Optimization and Operations Research” (PGMO), supported by EDF and the Fondation Mathématique Jacques Hadamard (FMJH). The authors also need to thank the referees for their careful reading of the manuscript and their numerous helpful comments.
- 1.Alvarez, F., Attouch, H.: An inertial proximal method for maximal monotone operators via discretization of a nonlinear oscillator with damping. Set-Valued Anal. 9(1–2), 3–11 (2001)Google Scholar
- 8.Combettes, P.L., Condat, L., Pesquet, J.-C., Vũ, B.C.: A forward–backward view of some primal–dual optimization methods in image recovery. In: Proceedings ICIP 2014 Conference, Paris, Oct. 2014 (2014) (to appear)Google Scholar
- 10.Davis, D., Yin, W.: A three-operator splitting scheme and its optimization applications. Technical report, CAM Report 15-13/preprint arXiv:1504.01032 (2015)
- 12.Duchi, J., Shalev-Shwartz, S., Singer, Y., Chandra, T.: Efficient projections onto the \(\ell _1\)-ball for learning in high dimensions. In: Proceedings of the 25th international conference on machine learning, ICML ’08, pages 272–279, New York (2008). ACMGoogle Scholar
- 18.Hohage, T., Homann, C.: A generalization of the Chambolle–Pock algorithm to Banach spaces with applications to inverse problems. Technical report, arXiv:1412.0126 (2014)
- 21.Nemirovski, A.S., Yudin, D.: Problem Complexity and Method Efficiency in Optimization. Wiley, New York (1983). Translated from the Russian and with a preface by E.R. Dawson, Wiley-Interscience Series in Discrete MathematicsGoogle Scholar
- 25.Pesquet, J.-C., Repetti, A.: A class of randomized primal–dual algorithms for distributed optimization. arXiv:1406.6404 (2014)
- 26.Pock, T., Cremers, D., Bischof, H., Chambolle, A.: An algorithm for minimizing the Mumford-Shah functional. In: ICCV Proceedings, LNCS. Springer (2009)Google Scholar
- 30.Tseng, P.: On accelerated proximal gradient methods for convex–concave optimization (2008). SIAM J. Optim. http://www.csie.ntu.edu.tw/~b97058/tseng/papers/apgm. (submitted)