Abstract
This paper addresses the problem of non-Bayesian learning in multi-agent networks, where agents repeatedly collect local observations about an unknown state of the world, and try to collaboratively detect the true state through information exchange. We focus on the impact of failures and asynchrony – two fundamental factors in distributed systems – on the performance of consensus-based non-Bayesian learning. In particular, we assume the networked agents may suffer crash faults, and messages delay can be arbitrarily long but finite.
-
1.
We characterize the minimal global identifiability of the network for any consensus-based non-Bayesian learning to work.
-
2.
Finite time convergence rate is obtained.
-
3.
As part of our convergence analysis, we obtain a generalization of a celebrated result by Wolfowitz and Hajnal to submatrices, which might be of independent interest.
This research is supported in part by National Science Foundation award NSF 1329681. Any opinions, findings, and conclusions or recommendations expressed here are those of the authors and do not necessarily reflect the views of the funding agencies or the U.S. government.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In this paper, every vector considered is column vector.
- 2.
In the notation \(\mu _{t}^i\), the superscript denotes agents and subscript denotes iterations.
- 3.
For a given graph, a node s is called a sink if it has no outgoing links.
References
Chamberland, J.-F., Veeravalli, V.V.: Decentralized detection in sensor networks. IEEE Trans. Signal Process. 51(2), 407–416 (2003)
Feldman, M., Immorlica, N., Lucier, B., Weinberg, S.M.: Reaching consensus via non-Bayesian asynchronous learning in social networks. CoRR, abs/1408.5192 (2014)
Gale, D., Kariv, S.: Bayesian learning in social networks. Games Econ. Behav. 45(2), 329–346 (2003)
Hajnal, J., Bartlett, M.: Weak ergodicity in non-homogeneous Markov chains. In: Mathematical Proceedings of the Cambridge Philosophical Society, vol. 54, pp. 233–246. Cambridge Univ Press (1958)
Jadbabaie, A., Molavi, P., Sandroni, A., Tahbaz-Salehi, A.: Non-Bayesian social learning. Games Econ. Behav. 76(1), 210–225 (2012)
Jadbabaie, A., Molavi, P., Tahbaz-Salehi, A.: Information heterogeneity and the speed of learning in social networks. Columbia Business School Research Paper, (13–28) (2013)
Lalitha, A., Sarwate, A., Javidi, T.: Social learning and distributed hypothesis testing. In: IEEE International Symposium on Information Theory, pp. 551–555. IEEE (2014)
Lynch, N.A.: Distributed Algorithms. Morgan Kaufmann, San Francisco (1996)
Molavi, P., Tahbaz-Salehi, A., Jadbabaie, A.: Foundations of non-Bayesian social learning. Columbia Business School Research Paper (2015)
Nedić, A., Olshevsky, A., Uribe, C.A.: Nonasymptotic convergence rates for cooperative learning over time-varying directed graphs. In: American Control Conference (ACC), pp. 5884–5889. IEEE (2015)
Rad, K.R., Tahbaz-Salehi, A.: Distributed parameter estimation in networks. In: 49th IEEE Conference on Decision and Control (CDC), pp. 5050–5055. IEEE (2010)
Shahrampour, S., Jadbabaie, A.: Exponentially fast parameter estimation in networks using distributed dual averaging. In: 52nd IEEE Conference on Decision and Control, pp. 6196–6201. IEEE (2013)
Shahrampour, S., Rakhlin, A., Jadbabaie, A.: Distributed detection: finite-time analysis and impact of network topology (2014)
Shahrampour, S., Rakhlin, A., Jadbabaie, A.: Finite-time analysis of the distributed detection problem. CoRR, abs/1512.09311 (2015)
Su, L., Vaidya, N.H.: Asynchronous distributed hypothesis testing in the presence of crash failures. University of Illinois at Urbana-Champaign, Technical report (2016)
Su, L., Vaidya, N.H.: Non-Bayesian learning in the presence of Byzantine agents. In: Gavoille, C., Ilcinkas, D. (eds.) DISC 2016. LNCS, vol. 9888, pp. 414–427. Springer, Heidelberg (2016). doi:10.1007/978-3-662-53426-7_30
Tseng, L.: Fault-tolerant consensus and shared memory consistency model. Ph.D dissertation University of Illinois at Urbana-Champaign (2015)
Tsitsiklis, J.N.: Decentralized detection. In: Advances in Statistical Signal Processing, pp. 297–344. JAI Press (1993)
Varshney, P.K.: Distributed Bayesian detection: parallel fusion network. Distributed Detection and Data Fusion, pp. 36–118. Springer, New York (1997)
Wolfowitz, J.: Products of indecomposable, aperiodic, stochastic matrices. Proc. Am. Math. Soc. 14(5), 733–737 (1963)
Wong, E., Hajek, B.: Stochastic Processes in Engineering Systems. Springer Science & Business Media, New York (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Su, L., Vaidya, N.H. (2016). Asynchronous Non-Bayesian Learning in the Presence of Crash Failures. In: Bonakdarpour, B., Petit, F. (eds) Stabilization, Safety, and Security of Distributed Systems. SSS 2016. Lecture Notes in Computer Science(), vol 10083. Springer, Cham. https://doi.org/10.1007/978-3-319-49259-9_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-49259-9_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49258-2
Online ISBN: 978-3-319-49259-9
eBook Packages: Computer ScienceComputer Science (R0)