Abstract
We study distributed algorithms for solving global optimization problems in which the objective function is the sum of local objective functions of agents and the constraint set is given by the intersection of local constraint sets of agents. We assume that each agent knows only his own local objective function and constraint set, and exchanges information with the other agents over a randomly varying network topology to update his information state. We assume a state-dependent communication model over this topology: communication is Markovian with respect to the states of the agents and the probability with which the links are available depends on the states of the agents. We study a projected multi-agent subgradient algorithm under state-dependent communication. The state-dependence of the communication introduces significant challenges and couples the study of information exchange with the analysis of subgradient steps and projection errors. We first show that the multi-agent subgradient algorithm when used with a constant stepsize may result in the agent estimates to diverge with probability one. Under some assumptions on the stepsize sequence, we provide convergence rate bounds on a “disagreement metric” between the agent estimates. Our bounds are time-nonhomogeneous in the sense that they depend on the initial starting time. Despite this, we show that agent estimates reach an almost sure consensus and converge to the same optimal solution of the global optimization problem with probability one under different assumptions on the local constraint sets and the stepsize sequence.
Similar content being viewed by others
References
Acemoglu D., Ozdaglar A., ParandehGheibi A.: Spread of (mis)information in social networks. Games Econ. Behav. 70, 194–227 (2010)
Bertsekas D.P., Nedić A., Ozdaglar A.E.: Convex analysis and optimization. Athena Scientific, Cambridge, MA (2003)
Bertsekas D.P., Tsitsiklis J.N.: Parallel and Distributed Computation: Numerical Methods. Athena Scientific, Belmont, MA (1997)
Blondel V.D., Hendrickx J.M., Tsitsiklis J.N.: On Krause’s multi-agent consensus model with state-dependent connectivity. IEEE Trans. Automat. Control 54(11), 2586–2597 (2009)
Blondel V.D., Hendrickx J.M., Tsitsiklis J.N.: Continuous-time average-preserving opinion dynamics with opinion-dependent communications. SIAM J. Control Optim. 48(8), 5214–5240 (2010)
Blondel, V.D., Hendrickx, J.M., Olshevsky, A., Tsitsiklis, J.N.: Convergence in multiagent coordination, consensus, and flocking. In: Proceedings of IEEE CDC (2005)
Boyd, S., Ghosh, A., Prabhakar, B., Shah, D.: Gossip algorithms: design, analysis, and applications. In: Proceedings of IEEE INFOCOM (2005)
Cao, M., Spielman, D.A., Morse, A.S.: A lower bound on convergence of a distributed network consensus algorithm. In: Proceedings of IEEE CDC (2005)
Duchi, J., Agarwal, A., Wainwright, M.: Dual averaging for distributed optimization: Convergence analysis and network scaling, Preprint (2010)
Fagnani F., Zampieri S.: Randomized consensus algorithms over large scale networks. IEEE J. Sel. Areas Commun. 26, 634–649 (2008)
Golub B., Jackson M.O.: Naive learning in social networks: Convergence, influence, and the wisdom of crowds. Am. Econ. J. Microecon. 2(1), 112–149 (2010)
Hatano Y., Mesbahi M.: Agreement over random networks. IEEE Trans. Automat. Control 50(11), 1867–1872 (2005)
Jadbabaie A., Lin J., Morse S.: Coordination of groups of mobile autonomous agents using nearest neighbor rules. IEEE Trans. Automat. Control 48(6), 988–1001 (2003)
Lobel, I., Ozdaglar, A.: Distributed subgradient methods for convex optimization over random networks. IEEE Trans. Automat. Control (2011) (to appear)
Lobel, I., Ozdaglar, A., Feijer, D.: Online appendices of distributed multi-agent optimization with state-dependent communication, http://www.pages.stern.nyu.edu/~ilobel/state-dep-online-app.pdf (2011)
Matei, I., Baras, J.: Distributed subgradient method under random communication topology—the effect of the probability distribution of the random graph on the performance metrics, ISR Technical Report 2009-15 (2009)
Nedić A., Olshevsky A., Ozdaglar A., Tsitsiklis J.N.: On distributed averaging algorithms and quantization effects. IEEE Trans. Automat. Control 54(11), 2506–2517 (2009)
Nedić A., Ozdaglar A.: Distributed subgradient methods for multi-agent optimization. IEEE Trans. Automat. Control 54(1), 48–61 (2009)
Nedić A., Ozdaglar A., Parrilo P.A.: Constrained consensus and optimization in multi-agent networks. IEEE Trans. Automat. Control 55, 922–938 (2010)
Nesterov Y.: Primal-dual subgradient methods for convex problems. Math. Program. 120(1), 261–283 (2009)
Olfati-Saber R., Murray R.M.: Consensus problems in networks of agents with switching topology and time-delays. IEEE Trans. Automat. Control 49(9), 1520–1533 (2004)
Olshevsky A., Tsitsiklis J.N.: Convergence speed in distributed consensus and averaging. SIAM J. Control Optim. 48(1), 33–55 (2009)
Ram S.S., Nedić A., Veeravalli V.V.: Incremental stochastic subgradient algorithms for convex optimization. SIAM J. Optim. 20(2), 691–717 (2009)
Tahbaz-Salehi A., Jadbabaie A.: A necessary and sufficient condition for consensus over random networks. IEEE Trans. Automat. Control 53(3), 791–795 (2008)
Tsitsiklis J.N., Bertsekas D.P., Athans M.: Distributed asynchronous deterministic and stochastic gradient optimization algorithms. IEEE Trans. Automat. Control 31(9), 803–812 (1986)
Wu C.W.: Synchronization and convergence of linear dynamics in random directed networks. IEEE Trans. Automat. Control 51(7), 1207–1210 (2006)
Zhu, M., Martínez, S.: On distributed convex optimization under inequality and equality constraints via primal-dual subgradient methods, unpublished manuscript (2010)
Author information
Authors and Affiliations
Corresponding author
Additional information
This paper is dedicated to the memory of Paul Tseng, a great researcher and friend.
This research was partially supported by the National Science Foundation under Career grant DMI-0545910, the DARPA ITMANET program, and the AFOSR MURI R6756-G2.
Electronic Supplementary Material
The Below is the Electronic Supplementary Material.
Rights and permissions
About this article
Cite this article
Lobel, I., Ozdaglar, A. & Feijer, D. Distributed multi-agent optimization with state-dependent communication. Math. Program. 129, 255–284 (2011). https://doi.org/10.1007/s10107-011-0467-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10107-011-0467-x