Abstract
A block decomposition method is proposed for minimizing a (possibly non-convex) continuously differentiable function subject to one linear equality constraint and simple bounds on the variables. The proposed method iteratively selects a pair of coordinates according to an almost cyclic strategy that does not use first-order information, allowing us not to compute the whole gradient of the objective function during the algorithm. Using first-order search directions to update each pair of coordinates, global convergence to stationary points is established for different choices of the stepsize under an appropriate assumption on the level set. In particular, both inexact and exact line search strategies are analyzed. Further, linear convergence rate is proved under standard additional assumptions. Numerical results are finally provided to show the effectiveness of the proposed method.
Similar content being viewed by others
References
Beck, A.: The 2-coordinate descent method for solving double-sided simplex constrained minimization problems. J. Optim. Theory Appl. 162(3), 892–919 (2014)
Beck, A., Tetruashvili, L.: On the convergence of block coordinate descent type methods. SIAM J. Optim. 23(4), 2037–2060 (2013)
Bertsekas, D.P.: Projected Newton methods for optimization problems with simple constraints. SIAM J. Control Optim. 20(2), 221–246 (1982)
Bomze, I.M., Rinaldi, F., Rota Bulò, S.: First-order methods for the impatient: support identification in finite time with convergent Frank-Wolfe variants. Optimization Online (2018). http://www.optimization-online.org/DB_HTML/2018/07/6694.html
Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pp. 144–152. ACM (1992)
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 27 (2011)
Chang, K.W., Hsieh, C.J., Lin, C.J.: Coordinate descent method for large-scale l2-loss linear support vector machines. J. Mach. Learn. Res. 9, 1369–1398 (2008)
Cristofari, A., De Santis, M., Lucidi, S., Rinaldi, F.: An active-set algorithmic framework for non-convex optimization problems over the simplex (2018). arXiv preprint arXiv:1703.07761
Fan, R.E., Chen, P.H., Lin, C.J.: Working set selection using second order information for training support vector machines. J. Mach. Learn. Res. 6, 1889–1918 (2005)
Hsieh, C.J., Chang, K.W., Lin, C.J., Keerthi, S.S., Sundararajan, S.: A dual coordinate descent method for large-scale linear SVM. In: Proceedings of the 25th International Conference on Machine Learning, pp. 408–415. ACM (2008)
Joachims, T.: Making large-scale support vector machine learning practical. In: Schölkopf, B., Burges, C.J., Smola, A.J. (eds.) Advances in Kernel Methods—Support Vector Learning, B, pp. 169–184. MIT Press, Cambridge (1999)
Konnov, I.V.: Selective bi-coordinate variations for resource allocation type problems. Comput. Optim. Appl. 64(3), 821–842 (2016)
Lin, C.J.: On the convergence of the decomposition method for support vector machines. IEEE Trans. Neural Netw. 12(6), 1288–1298 (2001)
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)
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)
Lucidi, S., Palagi, L., Risi, A., Sciandrone, M.: A convergent decomposition algorithm for support vector machines. Comput. Optim. Appl. 38(2), 217–234 (2007)
Luo, Z.Q., Tseng, P.: On the convergence of the coordinate descent method for convex differentiable minimization. J. Optim. Theory Appl. 72(1), 7–35 (1992)
Manno, A., Palagi, L., Sagratella, S.: Parallel decomposition methods for linearly constrained problems subject to simple bound with application to the SVMs training. Comput. Optim. Appl. 71(1), 115–145 (2018)
Necoara, I.: Random coordinate descent algorithms for multi-agent convex optimization over networks. IEEE Trans. Autom. Control 58(8), 2001–2012 (2013)
Necoara, I., Nesterov, Y., Glineur, F.: Random block coordinate descent methods for linearly constrained optimization over networks. J. Optim. Theory Appl. 173(1), 227–254 (2017)
Necoara, I., Patrascu, A.: A random coordinate descent algorithm for optimization problems with composite objective function and linear coupled constraints. Comput. Optim. Appl. 57(2), 307–337 (2014)
Nesterov, Y.: Efficiency of coordinate descent methods on huge-scale optimization problems. SIAM J. Optim. 22(2), 341–362 (2012)
Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course, vol. 87. Springer, New York (2013)
Palagi, L., Sciandrone, M.: On the convergence of a modified version of SVM light algorithm. Optim. Methods Softw. 20(2–3), 317–334 (2005)
Patrascu, A., Necoara, I.: Efficient random coordinate descent algorithms for large-scale structured nonconvex optimization. J. Glob. Optim. 61(1), 19–46 (2015)
Platt, J.C.: Sequential minimal optimization: a fast algorithm for training support vector machines. In: Schölkopf, B., Burges, C.J., Smola, A.J. (eds.) Advances in Kernel Methods—Support Vector Learning, pp. 185–208. MIT Press, Cambridge (1998)
Raj, A., Olbrich, J., Gärtner, B., Schölkopf, B., Jaggi, M.: Screening rules for convex problems (2016). arXiv preprint arXiv:1609.07478
Reddi, S., Hefny, A., Downey, C., Dubey, A., Sra, S.: Large-scale randomized-coordinate descent methods with non-separable linear constraints (2014). arXiv preprint arXiv:1409.2617
Tseng, P.: Descent methods for convex essentially smooth minimization. J. Optim. Theory Appl. 71(3), 425–463 (1991)
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)
Wright, S.J.: Coordinate descent algorithms. Math. Program. 151(1), 3–34 (2015)
Xiao, L., Boyd, S.: Optimal scaling of a gradient method for distributed resource allocation. J. Optim. Theory Appl. 129(3), 469–488 (2006)
Xu, S., Freund, R.M., Sun, J.: Solution methodologies for the smallest enclosing circle problem. Comput. Optim. Appl. 25(1–3), 283–292 (2003)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cristofari, A. An almost cyclic 2-coordinate descent method for singly linearly constrained problems. Comput Optim Appl 73, 411–452 (2019). https://doi.org/10.1007/s10589-019-00082-0
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10589-019-00082-0