Abstract
We consider distributed ordinal comparison of selecting the best option which maximizes the average of local reward function values among available options in a dynamic network. Each node in the network knows only his reward function, and edge-connectivity across the nodes changes over time by Calafiore’s model. To estimate each option’s global reward function value, local samples for each option are generated at each node and those are iteratively mixed over the network by a weighted average of local estimates of instantaneous neighbors. Each node selects an option that achieves the maximum of the current global estimates as an estimate of the best option. We establish a lower bound on the probability of correct local-selection at any node, which uniformly converges over the nodes to a lower bound on the probability of correct global-selection by a virtual centralized node with the total available samples.
References
Calafiore, G.C.: Distributed randomized algorithms for probabilistic performance analysis. Syst. Control Lett. 58, 202–212 (2009)
Ho, Y.C., Cassandras, C., Chen, C.-H., Dai, L.: Ordinal optimization and simulation. J. Oper. Res. Soc. 51, 490–500 (2000)
Rabbat, M., Nowak, R.: Distributed optimization in sensor networks. In: Proc. of the ACM/IEEE Int. Conf. on Information Processing in Sensor Networks, pp. 20–27 (2004)
Fu, M.C., Jin, X.: On the convergence rate of ordinal comparisons of random variables. IEEE Trans. Autom. Control 46, 1950–1954 (2001)
Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Found. Trends Mach. Learn. 47, 235–256 (2002)
Xiao, L., Boyd, S.: Fast linear iterations for distributed averaging. Syst. Control Lett. 53, 65–78 (2004)
Hoeffding, W.: Probability inequalities for sums of bounded random variables. J. Am. Stat. Assoc. 58, 13–30 (1963)
Chen, C.-H., Lin, J., Yücesan, E., Chick, S.E.: Simulation budget allocation for further enhancing the efficiency of ordinal optimization. Discrete Event Dyn. Syst. 10, 251–270 (2000)
Nedic, A., Ozdaglar, A.: Distributed subgradient methods for multi-agent optimization. IEEE Trans. Autom. Control 54(1), 48–61 (2009)
Chick, S.E., Inoue, K.: New two-stage and sequential procedures for selecting the best simulated system. Oper. Res. 49(5), 732–743 (2001)
Hong, L.J.: Fully sequential indifference-zone selection procedures with variance-dependent sampling. Nav. Res. Logist. 53, 464–476 (2006)
Kim, S.-H., Nelson, B.L.: A fully sequential procedure for indifference-zone selection in simulation. ACM Trans. Model. Comput. Simul. 11, 251–273 (2001)
Pichitlamken, J., Nelson, B.L., Hong, L.: A sequential procedure for neighborhood selection-of-the-best in optimization via simulation. Eur. J. Oper. Res. 173, 283–298 (2006)
Kim, S.-H., Nelson, B.L.: Recent advances in ranking and selection. In: Proc. of the 2007 Winter Simulation Conf., pp. 162–172 (2007)
Swisher, J.R., Jacobson, S.H.: A survey of ranking, selection, and multiple comparison procedures for discrete-event simulation. In: Proc. of the 1999 Winter Simulation Conf., pp. 492–501 (1999)
Acknowledgements
The work of H.S. Chang was supported by the Sogang University Research Grant of 2009 (200811037). The work of J. Hu was supported in part by the Air Force Office of Scientific Research under Grant FA95501010340, and by the National Science Foundation under Grants CMMI-0900332 and CMMI-1130761.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Qianchuan Zhao.
Rights and permissions
About this article
Cite this article
Chang, H.S., Hu, J. On the Probability of Correct Selection in Ordinal Comparison over Dynamic Networks. J Optim Theory Appl 155, 594–604 (2012). https://doi.org/10.1007/s10957-012-0082-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10957-012-0082-x