Abstract
This paper mainly proposes an parallel distributed learning algorithm for the robust convex optimization (RCO). Firstly, the scenario approach is used to transform RCO into its probabilistic approximation Scenario Problem (SP), which is distributively solved by multiprocessors to lighten the computational burden. Secondly, each processor (node) of the colored network processes the local optimization via a primal-dual subgradient algorithm (PDSA) to obtain an optimal solution called a local variable. Finally, a consensus method named the Colored Distributed Average Consensus (CDAC), which is based on Distributed Average Consensus (DAC), is proposed to act on the whole local variables to obtain the global optimal solution. Experimental results show that CDAC has an advantage in terms of computational time over DAC, while they have the same results.
Keywords
This study was supported by the National Natural Science Foundation of China under Grant no. 61672477.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ben-Tal, A., Nemirovski, A.: Robust convex optimization. Math. Oper. Res. 23, 769–805 (1998)
Bertsimas, D., Brown, D., Caramanis, C.: Theory and applications of robust optimization. SIAM Rev 53, 464–501 (2011)
Bertsimas, D., Thiele, A.: A robust optimization approach to inventory theory. Oper. Res. 54, 150–168 (2006)
Bertsimas, D., Sim, M.: Robust discrete optimization and network flows. Math. Program. 98, 49–71 (2003)
Ben-Tal, A., Hertog, D., Vial, J.: Deriving robust counterparts of nonlinear uncertain inequalities. Math. Program. 149, 265–299 (2015)
Calafiore, G., Campi, M.: Uncertain convex programs: randomized solutions and confidence levels. Math. Program. 102, 25–46 (2005)
Campi, M., Garatti, S.: The exact feasibility of randomized solutions of uncertain convex programs. SIAM J. Optim. 19, 1211–1230 (2008)
Farias, D., Roy, B.: On constraint sampling in the linear programming approach to approximate dynamic programming. Math. Oper. Res. 29, 462–478 (2004)
You, K., Tempo, R.: Networked parallel algorithms for robust convex optimization via the scenario spproach. arXiv preprint. arXiv: 1607.05507 (2016)
Scardapane, S., Wang, D., Panella, M., Uncini, A.: Distributed learning for random vector functional-link networks. Inf. Sci. 301, 271–284 (2015)
Alamo, T., Tempo, R., Luque, A., Ramirez, D.: Randomized methods for design of uncertain systems: sample complexity and sequential algorithms. Automatica 52, 160–172 (2013)
Sen, S., Sherali, H.: A class of convergent of primal-dual subgradient algorithms for decomposable convex program. Math. Program. 35, 279–297 (1986)
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends\(\textregistered \) Mach. Learn. 3, 1–122 (2011)
Xiao, L., Boyd, S.: Fast linear iterations for distributed averaging. Syst. Control Lett. 53, 65–78 (2004)
Olfati-Saber, R., Fax, J., Murray, R.: Consensus and cooperation in networked multi-agent systems. Proc. IEEE 95, 215–233 (2007)
Ghaoui, L., Lebret, H.: Robust solutions to least-squares problems with uncertain data. SIAM J. Matrix Anal. A. 18, 1035–1064 (1997)
Mota, J., Xavier, J., Aguiar, P., Püschel, M.: D-ADMM: A communication-efficient distributed algorithm for separable optimization. IEEE Trans. Sig. Process. 61, 2718–2723 (2013)
Wang, H., Gao, Y., Shi, Y., Wang, R.: Group-based alternating direction method of multipliers for distributed linear classification. IEEE Trans. Cybern. 99, 1–15 (2016)
Wang, H., Gao, Y., Shi, Y., Wang, H.: A fast distributed classification algorithm for large-scale imbalanced data. In: 16th IEEE International Conference on Data Mining, pp. 1251–1256. IEEE, New Orleans (2016)
Goldstein, T., O’Donoghue, B., Setzer, S., Baraniuk, R.: Fast alternating direction optimization methods. SIAM J. Imaging. Sci. 7, 1588–1623 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Feng, F., Cao, F. (2017). Consensus-based Parallel Algorithm for Robust Convex Optimization with Scenario Approach in Colored Network. In: Yin, H., et al. Intelligent Data Engineering and Automated Learning – IDEAL 2017. IDEAL 2017. Lecture Notes in Computer Science(), vol 10585. Springer, Cham. https://doi.org/10.1007/978-3-319-68935-7_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-68935-7_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68934-0
Online ISBN: 978-3-319-68935-7
eBook Packages: Computer ScienceComputer Science (R0)