Distributed Gaussian learning over time-varying directed graphs

We present a distributed (non-Bayesian) learning algorithm for the problem of parameter estimation with Gaussian noise. The algorithm is expressed as explicit updates on the parameters of the Gaussian beliefs (i.e. means and precision). We show a convergence rate of O(1/k) with the constant term depending on the number of agents and the topology of the network. Moreover, we show almost sure convergence to the optimal solution of the estimation problem for the general case of time-varying directed graphs.

[1]  Anit Kumar Sahu,et al.  Distributed recursive composite hypothesis testing: Imperfect communication , 2016, 2016 IEEE International Symposium on Information Theory (ISIT).

[2]  Nitin H. Vaidya,et al.  Defending non-Bayesian learning against adversarial attacks , 2018, Distributed Computing.

[3]  Anit Kumar Sahu,et al.  Distributed Constrained Recursive Nonlinear Least-Squares Estimation: Algorithms and Asymptotics , 2016, IEEE Transactions on Signal and Information Processing over Networks.

[4]  Nitin H. Vaidya,et al.  Non-Bayesian Learning in the Presence of Byzantine Agents , 2016, DISC.

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

[6]  Angelia Nedic,et al.  Distributed learning with infinitely many hypotheses , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[7]  Angelia Nedic,et al.  Network independent rates in distributed learning , 2015, 2016 American Control Conference (ACC).

[8]  Bernard Chazelle,et al.  Gaussian Learning-Without-Recall in a dynamic social network , 2016, 2017 American Control Conference (ACC).

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

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

[11]  Gérard Biau,et al.  The Statistical Performance of Collaborative Inference , 2015, J. Mach. Learn. Res..

[12]  Angelia Nedic,et al.  A tutorial on distributed (non-Bayesian) learning: Problem, algorithms and results , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

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

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

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

[16]  Philippe Smets,et al.  Belief functions on real numbers , 2005, Int. J. Approx. Reason..

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

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