Mirror Prox algorithm for multi-term composite minimization and semi-separable problems
- 503 Downloads
In the paper, we develop a composite version of Mirror Prox algorithm for solving convex–concave saddle point problems and monotone variational inequalities of special structure, allowing to cover saddle point/variational analogies of what is usually called “composite minimization” (minimizing a sum of an easy-to-handle nonsmooth and a general-type smooth convex functions “as if” there were no nonsmooth component at all). We demonstrate that the composite Mirror Prox inherits the favourable (and unimprovable already in the large-scale bilinear saddle point case) Open image in new window efficiency estimate of its prototype. We demonstrate that the proposed approach can be successfully applied to Lasso-type problems with several penalizing terms (e.g. acting together \(\ell _1\) and nuclear norm regularization) and to problems of semi-separable structures considered in the alternating directions methods, implying in both cases methods with the Open image in new window complexity bounds.
KeywordsNumerical algorithms for variational problems Composite optimization Minimization problems with multi-term penalty Proximal methods
Mathematics Subject Classification65K10 65K05 90C06 90C25 90C47
Research of the first and the third authors was supported by the NSF Grant CMMI-1232623. Research of the second author was supported by the CNRS-Mastodons Project GARGANTUA, and the LabEx PERSYVAL-Lab (ANR-11-LABX-0025).
- 1.Andersen, E. D., Andersen, K. D.: The MOSEK optimization tools manual. http://www.mosek.com/fileadmin/products/6_0/tools/doc/pdf/tools.pdf
- 10.Deng, W., Lai, M.-J., Peng, Z., Yin, W.: Parallel multi-block admm with o (1/k) convergence, 2013. http://www.optimization-online.org/DB_HTML/2014/03/4282.html (2013)
- 13.Grant, M., Boyd, S.: CVX: Matlab software for disciplined convex programming, version 2.0 beta. http://cvxr.com/cvx (2013)
- 14.Juditsky, A., Nemirovski, A.: First-order methods for nonsmooth largescale convex minimization: I general purpose methods; ii utilizing problems structure. In: Sra, S., Nowozin, S., Wright, S. (eds.) Optimization for Machine Learning, pp. 121–183. The MIT Press, (2011)Google Scholar
- 15.Lemarchal, C., Nemirovskii, A., Nesterov, Y.: New variants of bundle methods. Math. Program. 69(1–3), 111–147 (1995)Google Scholar
- 19.Nemirovski, A., Rubinstein, R.: An efficient stochastic approximation algorithm for stochastic saddle point problems. In: Dror, M., L’Ecuyer, P., Szidarovszky, F. (eds.) Modeling Uncertainty and Examination of Stochastic Theory, Methods, and Applications, pp. 155–184. Kluwer Academic Publishers, Boston (2002)Google Scholar
- 22.Orabona, F., Argyriou, A., Srebro, N.: Prisma: Proximal iterative smoothing algorithm. arXiv preprint arXiv:1206.2372, (2012)
- 23.Ouyang, Y., Chen, Y., Lan, G., Pasiliao, E. Jr.: An accelerated linearized alternating direction method of multipliers, arXiv:1401.6607 (2014)
- 25.Scheinberg, K., Goldfarb, D., Bai, X.: Fast first-order methods for composite convex optimization with backtracking. http://www.optimization-online.org/DB_FILE/2011/04/3004.pdf (2011)
- 27.Tseng, P.: On accelerated proximal gradient methods for convex–concave optimization. SIAM J. Optim. (2008, submitted)Google Scholar