Abstract
This paper addresses the problem of non-Bayesian learning over multi-agent networks, where agents repeatedly collect partially informative observations about an unknown state of the world, and try to collaboratively learn the true state. We focus on the impact of the Byzantine agents on the performance of consensus-based non-Bayesian learning. Our goal is to design an algorithm for the non-faulty agents to collaboratively learn the true state through local communication.
We propose an update rule wherein each agent updates its local beliefs as (up to normalization) the product of (1) the likelihood of the cumulative private signals and (2) the weighted geometric average of the beliefs of its incoming neighbors and itself (using Byzantine consensus). Under mild assumptions on the underlying network structure and the global identifiability of the network, we show that all the non-faulty agents asymptotically agree on the true state almost surely.
This research is supported in part by National Science Foundation awards NSF 1329681 and 1421918. 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 a column vector.
References
Bajovic, D., Jakovetic, D., Moura, J.M., Xavier, J., Sinopoli, B.: Large deviations performance of consensus+ innovations distributed detection with non-gaussian observations. IEEE Trans. Signal Process. 60(11), 5987–6002 (2012)
Cattivelli, F.S., Sayed, A.H.: Distributed detection over adaptive networks using diffusion adaptation. IEEE Trans. Signal Process. 59(5), 1917–1932 (2011)
Chamberland, J.-F., Veeravalli, V.V.: Decentralized detection in sensor networks. IEEE Trans. Signal Process. 51(2), 407–416 (2003)
Dolev, D., Lynch, N.A., Pinter, S.S., Stark, E.W., Weihl, W.E.: Reaching approximate agreement in the presence of faults. J. ACM 33(3), 499–516 (1986)
Fekete, A.D.: Asymptotically optimal algorithms for approximate agreement. Distrib. Comput. 4(1), 9–29 (1990)
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 University 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)
Jakovetic, D., Moura, J.M., Xavier, J.: Distributed detection over noisy networks: large deviations analysis. IEEE Trans. Signal Process. 60(8), 4306–4320 (2012)
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)
Mendes, H., Herlihy, M.: Multidimensional approximate agreement in Byzantine asynchronous systems. In: Proceedings of the Forty-fifth Annual ACM Symposium on Theory of Computing, STOC 2013, pp. 391–400. ACM, New York (2013)
Molavi, P., Tahbaz-Salehi, A., Jadbabaie, A.: Foundations of non-bayesian social learning. Columbia Business School Research Paper (2015)
Nedic, A., Olshevsky, A., Uribe, C.A.: Nonasymptotic convergence rates for cooperative learning over time-varying directed graphs. ArXiv e-prints 1410.1977 (2014)
Pease, M., Shostak, R., Lamport, L.: Reaching agreement in the presence of faults. J. ACM 27(2), 228–234 (1980)
Perles, M.A., Sigron, M.: A generalization of tverberg’s theorem. ArXiv e-prints 0710.4668 (2007)
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. In: 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp. 598–603. IEEE (2015)
Su, L., Vaidya, N.: Reaching approximate Byzantine consensus with multi-hop communication. In: Pelc, A., Schwarzmann, A.A. (eds.) SSS 2015. LNCS, vol. 9212, pp. 21–35. Springer, Heidelberg (2015)
Su, L., Vaidya, N.H.: Defending non-Bayesian learning against adversarial attacks. ArXiv e-prints, June 2016
Tsitsiklis, J.N.: Decentralized detection by a large number of sensors. Math. Control Signals Syst. 1(2), 167–182 (1988)
Vaidya, N.H.: Iterative Byzantine vector consensus in incomplete graphs. In: Chatterjee, M., Cao, J., Kothapalli, K., Rajsbaum, S. (eds.) ICDCN 2014. LNCS, vol. 8314, pp. 14–28. Springer, Heidelberg (2014)
Vaidya, N.H., Garg, V.K.: Byzantine vector consensus in complete graphs. In: Proceedings of the ACM Symposium on Principles of Distributed Computing, PODC 2013, pp. 65–73. ACM, New York (2013)
Vaidya, N.H., Tseng, L., Liang, G.: Iterative approximate Byzantine consensus in arbitrary directed graphs. In: Proceedings of the ACM Symposium on Principles of Distributed Computing, pp. 365–374. ACM (2012)
Varshney, P.K.: Distributed bayesian detection: Parallel fusion network. In: 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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Su, L., Vaidya, N.H. (2016). Non-Bayesian Learning in the Presence of Byzantine Agents. In: Gavoille, C., Ilcinkas, D. (eds) Distributed Computing. DISC 2016. Lecture Notes in Computer Science(), vol 9888. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-53426-7_30
Download citation
DOI: https://doi.org/10.1007/978-3-662-53426-7_30
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-53425-0
Online ISBN: 978-3-662-53426-7
eBook Packages: Computer ScienceComputer Science (R0)