Network independent rates in distributed learning

We propose a novel belief update algorithm for Distributed Non-Bayesian learning over time-varying directed graphs, where a group of agents tries to collectively select a distribution that best describes the observed data. We show that the proposed update rule, inspired by the Push-Sum algorithm, is consistent; moreover we provide an explicit characterization of its convergence rate. Our main result states that, after a transient time, all agents will concentrate their beliefs at a network independent rate. Network independent rates were not available for other consensus based distributed learning algorithms on time-varying directed graphs.

[1]  Kamiar Rahnama Rad,et al.  Distributed parameter estimation in networks , 2010, 49th IEEE Conference on Decision and Control (CDC).

[2]  Elchanan Mossel,et al.  Asymptotic learning on Bayesian social networks , 2012, Probability Theory and Related Fields.

[3]  Johannes Gehrke,et al.  Gossip-based computation of aggregate information , 2003, 44th Annual IEEE Symposium on Foundations of Computer Science, 2003. Proceedings..

[4]  S. Venkatesh,et al.  Distributed Bayesian hypothesis testing in sensor networks , 2004, Proceedings of the 2004 American Control Conference.

[5]  Elchanan Mossel,et al.  Strategic Learning and the Topology of Social Networks , 2012, ArXiv.

[6]  Alvaro Sandroni,et al.  Learning under social influence , 2009, Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference.

[7]  M. Alanyali,et al.  Distributed Detection in Sensor Networks With Packet Losses and Finite Capacity Links , 2006, IEEE Transactions on Signal Processing.

[8]  Asuman E. Ozdaglar,et al.  Convergence of rule-of-thumb learning rules in social networks , 2008, 2008 47th IEEE Conference on Decision and Control.

[9]  Ali Jadbabaie,et al.  Non-Bayesian Social Learning , 2011, Games Econ. Behav..

[10]  Shahin Shahrampour,et al.  Switching to learn , 2015, 2015 American Control Conference (ACC).

[11]  Shahin Shahrampour,et al.  Learning without recall by random walks on directed graphs , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[12]  Ilan Lobel,et al.  BAYESIAN LEARNING IN SOCIAL NETWORKS , 2008 .

[13]  T. Javidi,et al.  Social learning and distributed hypothesis testing , 2014, 2014 IEEE International Symposium on Information Theory.

[14]  Douglas Gale,et al.  Bayesian learning in social networks , 2003, Games Econ. Behav..

[15]  Konstantinos I. Tsianos,et al.  Asynchronous decentralized optimization in heterogeneous systems , 2014, 53rd IEEE Conference on Decision and Control.

[16]  Angelia Nedić,et al.  Fast Convergence Rates for Distributed Non-Bayesian Learning , 2015, IEEE Transactions on Automatic Control.

[17]  Michael G. Rabbat,et al.  Push-Sum Distributed Dual Averaging for convex optimization , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

[18]  M. Degroot.  Reaching a Consensus , 1974 .

[19]  Angelia Nedic,et al.  Nonasymptotic convergence rates for cooperative learning over time-varying directed graphs , 2014, 2015 American Control Conference (ACC).

[20]  Angelia Nedic,et al.  Distributed Optimization Over Time-Varying Directed Graphs , 2015, IEEE Trans. Autom. Control..

[21]  Shahin Shahrampour,et al.  Distributed Detection: Finite-Time Analysis and Impact of Network Topology , 2014, IEEE Transactions on Automatic Control.

[22]  Shahin Shahrampour,et al.  Exponentially fast parameter estimation in networks using distributed dual averaging , 2013, 52nd IEEE Conference on Decision and Control.

[23]  Colin McDiarmid,et al.  Surveys in Combinatorics, 1989: On the method of bounded differences , 1989 .

[24]  Robert D. Nowak,et al.  Decentralized source localization and tracking [wireless sensor networks] , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[25]  Matthew O. Jackson,et al.  Naïve Learning in Social Networks and the Wisdom of Crowds , 2010 .

[26]  Yurii Nesterov,et al.  Primal-dual subgradient methods for convex problems , 2005, Math. Program..

[27]  John N. Tsitsiklis,et al.  Weighted Gossip: Distributed Averaging using non-doubly stochastic matrices , 2010, 2010 IEEE International Symposium on Information Theory.

[28]  Walid Hachem,et al.  Analysis of Sum-Weight-Like Algorithms for Averaging in Wireless Sensor Networks , 2012, IEEE Transactions on Signal Processing.