Abstract
This paper considers the problem of minimizing a continuously differentiable function with a Lipschitz continuous gradient subject to a single linear equality constraint and additional bound constraints on the decision variables. We introduce and analyze several variants of a 2-coordinate descent method: a block descent method that performs an optimization step with respect to only two variables at each iteration. Based on two new optimality measures, we establish convergence to stationarity points for general nonconvex objective functions. In the convex case, when all the variables are lower bounded but not upper bounded, we show that the sequence of function values converges at a sublinear rate. Several illustrative numerical examples demonstrate the effectiveness of the method.
Similar content being viewed by others
References
Bertsekas, D.P., Tsitsiklis, J.N.: Parallel and Distributed Computation. Prentice-Hall, Englewood Cliffs (1989)
Ortega, J.M., Rheinboldt, W.C.: Iterative Solution of Nonlinear Equations in Several Variables. Academic Press, New York (1970)
Auslender, A.: Méthodes numériques pour la décomposition et la minimisation de fonctions non différentiables. Numer. Math. 18, 213–223 (1971/72)
Auslender, A.: Optimisation. Méthodes Numériques, Maîtrise de Mathématiques et Applications Fondamentales. Masson, Paris (1976)
Auslender, A., Martinet, B.: Méthodes de décomposition pour la minimisation d’une fonctionnelle sur un espace produit. C. R. Acad. Sci. Paris Sér. A-B 274, A632–A635 (1972)
Bertsekas, D.P.: Nonlinear Programming, 2nd edn. Athena Scientific, Belmont (1999)
Cassioli, A., Lorenzo, D.D., Sciandrone, M.: On the convergence of inexact block coordinate descent methods for constrained optimization. Eur. J. Oper. Res. 231(2), 274–281 (2013)
Cassioli, A., Sciandrone, M.: A convergent decomposition method for box constrained optimization problems. Optim. Lett. 3(3), 397–409 (2009)
Grippo, L., Sciandrone, M.: Globally convergent block-coordinate techniques for unconstrained optimization. Optim. Methods Softw. 10, 587–637 (1999)
Luo, T., Tseng, P.: Error bounds and convergence analysis of feasible descent methods: a general approach. Ann. Oper. Reas. 46, 157–178 (1993)
Powell, M.J.D.: On search directions for minimization algorithms. Math. Program. 4, 193–201 (1973)
Luo, T., Tseng, P.: On the convergence of the coordinate descent method for convex differentiable minimization. J. Optim. Theory Appl. (1992)
Polak, E., Sargent, R.W.H., Sebastian, D.J.: On the convergence of sequential minimization algorithms. J. Optim. Theory Appl. 14, 439–442 (1974)
Sargent, R.W.H., Sebastian, D.J.: On the convergence of sequential minimization algorithms. J. Optim. Theory Appl. 12, 567–575 (1973)
Tseng, P., Yun, S.: A coordinate gradient descent method for nonsmooth separable minimization. Math. Program. 117, 387–423 (2009)
Nesterov, Y.: Efficiency of coordinate descent methods on huge-scale optimization problems (2010). CORE Discussion paper 2010/2
Beck, A., Tetruashvili, L.: On the convergence of block coordinate descent type methods. SIAM J. Optim. 23(2), 2037–2060 (2013)
Burges, C.J.C.: A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2, 121–167 (1998)
Platt, J.C.: Sequential minimal optimization: a fast algorithm for training support vector machines. In: Scholkopf, B., Burges, C.J.C., Smola, A.J. (eds.) Advances in Kernel Methods—Support Vector Learning, pp. 185–208. MIT Press, Cambridge (1999)
Keerthi, S., Gilbert, E.: Convergence of a generalized SMO algorithm for SVM. Mach. Learn. 46, 351–360 (2002)
Keerthi, S.S., Shevade, S.K., Bhattacharyya, C., Murthy, K.R.K.: Improvements to Platt’s SMO algorithm for SVM classifier design. Neural Comput. 13(3), 637–649 (2001)
Joachims, T.: Making large-scale SVM learning practical. In: Scholkopf, B., Burges, C.J.C., Smola, A.J. (eds.) Advances in Kernel Methods—Support Vector Learning, B, pp. 169–184. MIT Press, Cambridge (1999)
Lin, C.J.: On the convergence of the decomposition method for support vector machines. IEEE Trans. Neural Netw. 12, 1288–1298 (2001)
Lin, C.J.: Asymptotic convergence of an SMO algorithm without any assumptions. IEEE Trans. Neural Netw. 13, 248–250 (2002)
Palagi, L., Sciandrone, M.: On the convergence of a modified version of \(\rm \mathrm{SVM}^{\mathrm{light}}\) algorithm. Optim. Methods Softw. 20(2–3), 317–334 (2005)
Lucidi, S., Palagi, L., Risi, A., Sciandrone, M.: A convergent hybrid decomposition algorithm model for SVM training. IEEE Trans. Neural Netw. 20(6), 1055–1060 (2009)
Lin, C.J., Lucidi, S., Palagi, L., Risi, A., Sciandrone, M.: Decomposition algorithm model for singly linearly-constrained problems subject to lower and upper bounds. J. Optim. Theory Appl. 141(1), 107–126 (2009)
Lucidi, S., Palagi, L., Risi, A., Sciandrone, M.: A convergent decomposition algorithm for support vector machines. Comput. Optim. Appl. 38(2), 217–234 (2007)
Chen, P.H., Fan, R.E., Lin, C.J.: Working set selection using second order information for training support vector machines. J. Mach. Learn. Res. 6, 1889–1918 (2005)
Glasmachers, T., Igel, C.: Maximum-gain working set selection for SVMs. J. Mach. Learn. Res. 7, 1437–1466 (2006)
Chang, C.C., Hsu, C.W., Lin, C.J.: The analysis of decomposition methods for support vector machines. IEEE Trans. Neural Netw. 11, 1003–1008 (2000)
Dai, Y.H., Fletcher, R.: New algorithms for singly linearly constrained quadratic programs subject to lower and upper bounds. Math. Program., Ser. A 106(3), 403–421 (2006)
Serafini, T., Zanghirati, G., Zanni, L.: Gradient projection methods for quadratic programs and applications in training support vector machines. Optim. Methods Softw. 20, 353–378 (2005)
Tseng, P., Yun, S.: A coordinate gradient descent method for linearly constrained smooth optimization and support vector machines training. Comput. Optim. Appl. 47(2), 179–206 (2010)
Liuzzi, G., Palagi, L., Piacentini, M.: On the convergence of a Jacobi-type algorithm for singly linearly-constrained problems subject to simple bounds. Optim. Lett. 5(2), 347–362 (2011)
Markowitz, H.: Portfolio selection. J. Finance 7, 77–91 (1952)
Bomze, I.M.: Evolution towards the maximum clique. J. Glob. Optim. 10(2), 143–164 (1997)
Xu, S., Freund, R.M., Sun, J.: Solution methodologies for the smallest enclosing circle problem. Comput. Optim. Appl. 25(1–3), 283–292 (2003). A tribute to Elijah (Lucien) Polak
Lin, C.J.: A formal analysis of stopping criteria of decomposition methods for support vector machines. IEEE Trans. Neural Netw. 13(5), 1045–1052 (2002)
Hush, D., Scovel, C.: Polynomial-time decomposition algorithms for support vector machines. Mach. Learn. 51(1), 51–71 (2003)
Beck, A., Teboulle, M.: Gradient-based algorithms with applications to signal recovery problems. In: Eldar, Y., Palomar, D. (eds.) Convex Optimization in Signal Processing and Communications. Cambridge University Press, Cambridge (2010)
Nesterov, Y.: Introductory Lectures on Convex Optimization. Kluwer, Boston (2004)
Polyak, B.T.: Introduction to Optimization. Translations Series in Mathematics and Engineering. Optimization Software, New York (1987)
Chen, P.H., Fan, R.E., Lin, C.J.: A study on SMO-type decomposition methods for support vector machines. IEEE Trans. Neural Netw. 17(4), 893–908 (2006)
Grant, M., Boyd, S.: CVX: Matlab software for disciplined convex programming, version 1.21. http://cvxr.com/cvx (2011)
Sturm, F.J.: Using SeDuMi 1.02, a Matlab toolbox for optimization over symmetric cones. Optim. Methods Softw. 11–12, 625–653 (1999)
Chang, C.C., Lin, C.J.: LIBSVM data: Classification, regression, and multi-label. http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011). Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
Acknowledgements
I would like to thank the three anonymous reviewers for their useful comments and additional references which helped to improve the presentation of the paper. This work was partially supported by ISF grant #25312 and by BSF grant 2008100.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Gianni Di Pillo.
Rights and permissions
About this article
Cite this article
Beck, A. The 2-Coordinate Descent Method for Solving Double-Sided Simplex Constrained Minimization Problems. J Optim Theory Appl 162, 892–919 (2014). https://doi.org/10.1007/s10957-013-0491-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10957-013-0491-5