Social learning and distributed hypothesis testing

This paper considers a problem of distributed hypothesis testing and social learning. Individual nodes in a network receive noisy (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The distributions are known locally at the nodes, but the true parameter/hypothesis is not known. An update rule is analyzed in which agents first perform a Bayesian update of their belief (distribution estimate) of the parameter based on their local observation, communicate these updates to their neighbors, and then perform a “non-Bayesian” linear consensus using the log-beliefs of their neighbors. The main result of this paper is that under mild assumptions, the belief of any agent in any incorrect parameter converges to zero exponentially fast, and the exponential rate of learning is a characterized by the network structure and the divergences between the observations' distributions.

[1]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

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

[3]  Rudolf Ahlswede,et al.  Hypothesis testing with communication constraints , 1986, IEEE Trans. Inf. Theory.

[4]  Te Han,et al.  Hypothesis testing with multiterminal data compression , 1987, IEEE Trans. Inf. Theory.

[5]  Maurizio Longo,et al.  Quantization for decentralized hypothesis testing under communication constraints , 1990, IEEE Trans. Inf. Theory.

[6]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[7]  H. Vincent Poor,et al.  Decentralized Sequential Detection with a Fusion Center Performing the Sequential Test , 1992, 1992 American Control Conference.

[8]  N. Fisher,et al.  Probability Inequalities for Sums of Bounded Random Variables , 1994 .

[9]  S. Amari,et al.  Error bound of hypothesis testing with data compression , 1994, Proceedings of 1994 IEEE International Symposium on Information Theory.

[10]  Shun-ichi Amari,et al.  Statistical Inference Under Multiterminal Data Compression , 1998, IEEE Trans. Inf. Theory.

[11]  M. Newman,et al.  The structure of scientific collaboration networks. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[12]  M. Newman,et al.  Scientific collaboration networks. II. Shortest paths, weighted networks, and centrality. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

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

[14]  Pramod K. Varshney,et al.  Channel aware decision fusion in wireless sensor networks , 2004, IEEE Transactions on Signal Processing.

[15]  Thomas M. Cover,et al.  Elements of information theory (2. ed.) , 2006 .

[16]  Stephen P. Boyd,et al.  Randomized gossip algorithms , 2006, IEEE Transactions on Information Theory.

[17]  L. Tong,et al.  Distributed Statistical Inference using Type Based Random Access over Multi-access Fading Channels , 2006, 2006 40th Annual Conference on Information Sciences and Systems.

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

[19]  J. Shamma,et al.  Belief consensus and distributed hypothesis testing in sensor networks , 2006 .

[20]  Venkatesh Saligrama,et al.  Distributed Tracking in Multihop Sensor Networks With Communication Delays , 2007, IEEE Transactions on Signal Processing.

[21]  Yajun Mei.  Asymptotic Optimality Theory for Decentralized Sequential Hypothesis Testing in Sensor Networks , 2008, IEEE Transactions on Information Theory.

[22]  Devavrat Shah,et al.  Fast Distributed Algorithms for Computing Separable Functions , 2005, IEEE Transactions on Information Theory.

[23]  Alessandro Panconesi,et al.  Concentration of Measure for the Analysis of Randomized Algorithms , 2009 .

[24]  Peter Willett,et al.  On the optimality of likelihood ratio test for local sensor decision rules in the presence of non-ideal channels , 2003 .

[25]  H. Vincent Poor,et al.  A Collaborative Training Algorithm for Distributed Learning , 2009, IEEE Transactions on Information Theory.

[26]  Soummya Kar,et al.  Distributed Consensus Algorithms in Sensor Networks: Quantized Data and Random Link Failures , 2007, IEEE Transactions on Signal Processing.

[27]  Kenneth E. Barner,et al.  Convergence of Consensus Models With Stochastic Disturbances , 2010, IEEE Transactions on Information Theory.

[28]  Soummya Kar,et al.  Gossip Algorithms for Distributed Signal Processing , 2010, Proceedings of the IEEE.

[29]  Aaron B. Wagner,et al.  Optimality of binning for distributed hypothesis testing , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

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

[31]  Alexandros G. Dimakis,et al.  Order-Optimal Consensus Through Randomized Path Averaging , 2010, IEEE Transactions on Information Theory.

[32]  Manuel Mueller-Frank,et al.  A general framework for rational learning in social networks , 2011 .

[33]  Tara Javidi,et al.  Active Sequential Hypothesis Testing , 2012, ArXiv.

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

[35]  José M. F. Moura,et al.  Large Deviations Performance of Consensus+Innovations Distributed Detection With Non-Gaussian Observations , 2011, IEEE Transactions on Signal Processing.

[36]  Distributed Parameter Estimation in Sensor Networks: Nonlinear Observation Models and Imperfect Communication , 2012, IEEE Trans. Inf. Theory.

[37]  Pooya Molavi,et al.  Information Heterogeneity and the Speed of Learning in Social Networks , 2013 .

[38]  H. Vincent Poor,et al.  QD-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through Consensus + Innovations , 2012, IEEE Trans. Signal Process..

[39]  Pascal Bianchi,et al.  Performance of a Distributed Stochastic Approximation Algorithm , 2012, IEEE Transactions on Information Theory.

[40]  Rick S. Blum,et al.  Broadcast-Based Consensus With Non-Zero-Mean Stochastic Perturbations , 2013, IEEE Transactions on Information Theory.

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

[42]  Yu Xiang,et al.  Interactive hypothesis testing against independence , 2013, 2013 IEEE International Symposium on Information Theory.

[43]  Elchanan Mossel,et al.  On the Speed of Social Learning , 2014, SSRN Electronic Journal.

[44]  Elchanan Mossel,et al.  Groupthink and the Failure of Information Aggregation in Large Groups , 2014 .

[45]  Tara Javidi,et al.  On the rate of learning in distributed hypothesis testing , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[46]  Tara Javidi,et al.  Large deviation analysis for learning rate in distributed hypothesis testing , 2015, 2015 49th Asilomar Conference on Signals, Systems and Computers.

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

[48]  Anit Kumar Sahu,et al.  Distributed Sequential Detection for Gaussian Shift-in-Mean Hypothesis Testing , 2014, IEEE Transactions on Signal Processing.

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

[50]  L. Breuer.  Introduction to Stochastic Processes , 2022, Statistical Methods for Climate Scientists.