Abstract
This paper is concerned with a distributed optimization problem with inequality constraint over a multiagent network. The objective function is the sum of multiple local convex functions, which can be nonsmooth. Based on graph theory and nonsmooth analysis, we propose a neural network with a time-varying auxiliary function. The boundedness of the state solution is demonstrated by using the properties of the auxiliary function. Moreover, it is proved that the designed neural network with any initial conditions reaches a consensus and converges to the global optimal solution. Finally, a numerical simulation is discussed to verify the theoretical results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aubin, J.P., Cellina, A.: Differential Inclusions: Set-valued Maps and Viability Theory. Springer-Verlag, Berlin (1984)
Clarke, F.H.: Optimization and Nonsmooth Analysis. SIAM, Philadelphia (1990)
Deng, Z., Liang, S., Hong, Y.: Distributed continuous-time algorithms for resource allocation problems over weight-balanced digraphs. IEEE Trans. Cybern. 48(11), 3116–3125 (2018)
Gharesifard, B., Corts, J.: Distributed continuous-time convex optimization on weight-balanced digraphs. IEEE Trans. Autom. Control 59(3), 781–786 (2014)
Gravina, R., Alinia, P., Ghasemzadeh, H., Fortino, G.: Multi-sensor fusion in body sensor networks: state-of-the-art and research challenges. Inf. Fusion 35, 68–80 (2016)
Hopefiled, J., Tank, D.: Neural computation of decisions in optimization problems. Biol. Cybern. 52(3), 141–152 (1985)
Jiang, X., Qin, S., Xue, X.: A penalty-like neurodynamic approach to constrained nonsmooth distributed convex optimization. Neurocomputing 377(15), 225–233 (2020)
Kennedy, M., Chua, L.: Neural networks for nonlinear programming. IEEE Trans. Circ. Syst. 35(5), 554–562 (1988)
Li, Q., Liu, Y., Zhu, L.: Neural network for nonsmooth pseudoconvex optimization with general constraints. Neurocomputing 131, 336–347 (2014)
Liu, N., Qin, S.: A neurodynamic approach to nonlinear optimization problems with affine equality and convex inequality constraints. Neural Netw. 109, 147–158 (2019)
Liu, N., Qin, S.: A novel neurodynamic approach to constrained complex-variable pseudoconvex optimization. IEEE Trans. Cybern. 49(11), 3946–3956 (2019). (Regular paper)
Liu, Q., Yang, S., Wang, J.: A collective neurodynamic approach to distributed constrained optimization. IEEE Trans. Neural Netw. Learn. Syst. 28(8), 1747–1758 (2017)
Qin, S., Xue, X.: A two-layer recurrent neural network for non-smooth convex optimization problems. IEEE Trans. Neural Netw. Learn. Syst. 26(6), 1149–1160 (2015). (Regular paper)
Qin, S., Yang, X., Xue, X., Song, J.: A one-layer recurrent neural network for pseudoconvex optimization problems with equality and inequality constraints. IEEE Trans. Cybern. 47(10), 3063–3074 (2017)
Wu, Y., Sun, X., Zhao, X., Shen, T.: Optimal control of Boolean control networks with average cost: a policy iteration approach. Automatica 100, 378–387 (2019)
Xue, X., Bian, W.: Subgradient-based neural networks for nonsmooth convex optimization problems. IEEE Trans. Circ. Syst. 55(8), 2378–2391 (2008)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wei, J., Qin, S., Bian, W. (2020). A Neural Network for Distributed Optimization over Multiagent Networks. In: Han, M., Qin, S., Zhang, N. (eds) Advances in Neural Networks – ISNN 2020. ISNN 2020. Lecture Notes in Computer Science(), vol 12557. Springer, Cham. https://doi.org/10.1007/978-3-030-64221-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-64221-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64220-4
Online ISBN: 978-3-030-64221-1
eBook Packages: Computer ScienceComputer Science (R0)