Abstract
In this paper we analyze the randomized block-coordinate descent (RBCD) methods proposed in Nesterov (SIAM J Optim 22(2):341–362, 2012), Richtárik and Takáč (Math Program 144(1–2):1–38, 2014) for minimizing the sum of a smooth convex function and a block-separable convex function, and derive improved bounds on their convergence rates. In particular, we extend Nesterov’s technique developed in Nesterov (SIAM J Optim 22(2):341–362, 2012) for analyzing the RBCD method for minimizing a smooth convex function over a block-separable closed convex set to the aforementioned more general problem and obtain a sharper expected-value type of convergence rate than the one implied in Richtárik and Takáč (Math Program 144(1–2):1–38, 2014). As a result, we also obtain a better high-probability type of iteration complexity. In addition, for unconstrained smooth convex minimization, we develop a new technique called randomized estimate sequence to analyze the accelerated RBCD method proposed by Nesterov (SIAM J Optim 22(2):341–362, 2012) and establish a sharper expected-value type of convergence rate than the one given in Nesterov (SIAM J Optim 22(2):341–362, 2012).
Similar content being viewed by others
References
Beck, A., Tetruashvili, L.: On the convergence of block coordinate descent type methods. SIAM J. Optim. 23(4), 2037–2060 (2013)
Chang, K.-W., Hsieh, C.-J., Lin, C.-J.: Coordinate descent method for large-scale \(l_2\)-loss linear support vector machines. J. Mach. Learn. Res. 9, 1369–1398 (2008)
Hong, M., Wang, X., Razaviyayn, M., Luo, Z.-Q.L.: Iteration complexity analysis of block coordinate descent methods. arXiv:1310.6957 (2013)
Hsieh, C.-J., Chang, K.-W., Lin, C.-J., Keerthi, S., Sundararajan, S.: A dual coordinate descent method for large-scale linear SVM. In Proceedings of the 25th International Conference on Machine Learning (ICML), pp. 408–415 (2008)
Leventhal, D., Lewis, A.S.: Randomized methods for linear constraints: convergence rates and conditioning. Math. Oper. Res. 35(3), 641–654 (2010)
Li, Y., Osher, S.: Coordinate descent optimization for \(l_1\) minimization with application to compressed sensing; a greedy algorithm. Inverse Probl. Imaging 3, 487–503 (2009)
Lu, Z., Xiao, L.: Randomized block coordinate non-monotone gradient method for a class of nonlinear programming. arXiv:1306.5918 (2013)
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 (2002)
Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course. Kluwer Academic Publishers, Boston (2004)
Nesterov, Y.: Gradient methods for minimizing composite objective function. Math. Program. 140(1), 125–161 (2013)
Nesterov, Y.: Efficiency of coordinate descent methods on huge-scale optimization problems. SIAM J. Optim. 22(2), 341–362 (2012)
Patrascu, A., Necoara, I.: Efficient random coordinate descent algorithms for large-scale structured nonconvex optimization. To appear in Journal of Global Optimization. arXiv:1305.4027 (2013)
Qin, Z., Scheinberg, K., Goldfarb, D.: Efficient block-coordinate descent algorithms for the group lasso. Math. Program. Comput. 5(2), 143–169 (2013)
Richtárik, P., Takáč, M.: Efficient serial and parallel coordinate descent method for huge-scale truss topology design. Oper. Res. Proc. pp. 27–32 (2012)
Richtárik, P., Takáč, M.: Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function. Math. Program. 144(1–2), 1–38 (2014)
Richtárik, P., Takáč, M.: Parallel coordinate descent methods for big data optimization. arXiv:1212.0873 (2012)
Saha, A., Tewari, A.: On the non-asymptotic convergence of cyclic coordinate descent methods. SIAM J. Optim. 23(1), 576–601 (2013)
Shalev-Shwartz, S., Tewari, A.: Stochastic methods for \(l_1\) regularized loss minimization. In Proceedings of the 26th International Conference on Machine Learning (ICML), pp. 929–936 (2009)
Shalev-Shwartz, S., Zhang, T.: Proximal stochastic dual coordinate ascent. arXiv:1211.2717 (2012)
Tappenden, R., Richtárik, P., Gondzio, J.: Inexact coordinate descent: complexity and preconditioning. arXiv:1304.5530 (2013)
Tseng, P.: Convergence of a block coordinate descent method for nondifferentiable minimization. J. Optim. Theory Appl. 109, 475–494 (2001)
Tseng, P., Yun, S.: Block-coordinate gradient descent method for linearly constrained nonsmooth separable optimization. J. Optim. Theory Appl. 140, 513–535 (2009)
Tseng, P., Yun, S.: A coordinate gradient descent method for nonsmooth separable minimization. Math. Program. 117, 387–423 (2009)
Wen, Z., Goldfarb, D., Scheinberg, K.: Block coordinate descent methods for semidefinite programming. In: Anjos, M.F., Lasserre, J.B. (eds.) Handbook on Semidefinite, Cone and Polynomial Optimization. Software and Applications, vol. 166, pp. 533–564. Springer, Berlin (2012)
Wright, S.J.: Accelerated block-coordinate relaxation for regularized optimization. SIAM J. Optim. 22, 159–186 (2012)
Wu, T., Lange, K.: Coordinate descent algorithms for lasso penalized regression. Ann. Appl. Stat. 2(1), 224–244 (2008)
Yun, S., Toh, K.-C.: A coordinate gradient descent method for \(l_1\)-regularized convex minimization. Comput. Optim. Appl. 48, 273–307 (2011)
Acknowledgments
The authors would like to thank the two anonymous referees for their constructive comments which substantially improved the presentation of the paper.
Author information
Authors and Affiliations
Corresponding author
Additional information
Zhaosong Lu: This author was supported in part by NSERC Discovery Grant.
Rights and permissions
About this article
Cite this article
Lu, Z., Xiao, L. On the complexity analysis of randomized block-coordinate descent methods. Math. Program. 152, 615–642 (2015). https://doi.org/10.1007/s10107-014-0800-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10107-014-0800-2
Keywords
- Randomized block-coordinate descent
- Accelerated coordinate descent
- Iteration complexity
- Convergence rate
- Composite minimization