Robust Asynchronous and Network-Independent Cooperative Learning

We consider the model of cooperative learning via distributed non-Bayesian learning, where a network of agents tries to jointly agree on a hypothesis that best described a sequence of locally available observations. Building upon recently proposed weak communication network models, we propose a robust cooperative learning rule that allows asynchronous communications, message delays, unpredictable message losses, and directed communication among nodes. We show that our proposed learning dynamics guarantee that all agents in the network will have an asymptotic exponential decay of their beliefs on the wrong hypothesis, indicating that the beliefs of all agents will concentrate on the optimal hypotheses. Numerical experiments provide evidence on a number of network setups.

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

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

[3]  Christoforos N. Hadjicostis,et al.  Distributed Averaging and Balancing in Network Systems: with Applications to Coordination and Control , 2018, Found. Trends Syst. Control..

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

[5]  Ali H. Sayed,et al.  Decentralized Consensus Optimization With Asynchrony and Delays , 2016, IEEE Transactions on Signal and Information Processing over Networks.

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

[7]  Jie Lin,et al.  Coordination of groups of mobile autonomous agents using nearest neighbor rules , 2003, IEEE Trans. Autom. Control..

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

[9]  Yashodhan Kanoria,et al.  Tractable Bayesian Social Learning on Trees , 2012, IEEE Journal on Selected Areas in Communications.

[10]  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).

[11]  Nikhil R. Devanur,et al.  Reaching Consensus via Non-Bayesian Asynchronous Learning in Social Networks , 2014, APPROX-RANDOM.

[12]  Ali Jadbabaie,et al.  A Theory of Non‐Bayesian Social Learning , 2018 .

[13]  Angelia Nedic,et al.  Distributed Learning for Cooperative Inference , 2017, ArXiv.

[14]  Shreyas Sundaram,et al.  A Communication-Efficient Algorithm for Exponentially Fast Non-Bayesian Learning in Networks , 2019, 2019 IEEE 58th Conference on Decision and Control (CDC).

[15]  Angelia Nedic,et al.  Distributed optimization over time-varying directed graphs , 2013, 52nd IEEE Conference on Decision and Control.

[16]  Ali Jadbabaie,et al.  On Malicious Agents in Non-Bayesian Social Learning with Uncertain Models , 2019, 2019 22th International Conference on Information Fusion (FUSION).

[17]  Lance Kaplan,et al.  Non-Bayesian Social Learning With Uncertain Models , 2020, IEEE Transactions on Signal Processing.

[18]  Shreyas Sundaram,et al.  A New Approach for Distributed Hypothesis Testing with Extensions to Byzantine-Resilience , 2019, 2019 American Control Conference (ACC).

[19]  Ye Tian,et al.  ASY-SONATA: Achieving Linear Convergence in Distributed Asynchronous Multiagent Optimization , 2018, 2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

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

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

[22]  Wee Peng Tay,et al.  Non-Bayesian social learning with observation reuse and soft switching , 2017, 2017 IEEE International Conference on Communications (ICC).

[23]  Ioannis Ch. Paschalidis,et al.  Robust Asynchronous Stochastic Gradient-Push: Asymptotically Optimal and Network-Independent Performance for Strongly Convex Functions , 2018, J. Mach. Learn. Res..

[24]  Ali H. Sayed,et al.  Belief Control Strategies for Interactions Over Weakly-Connected Graphs , 2018, IEEE Open Journal of Signal Processing.

[25]  Ali Jadbabaie,et al.  On Increasing Self-Confidence in Non-Bayesian Social Learning over Time-Varying Directed Graphs , 2018, 2019 American Control Conference (ACC).

[26]  Michael Athans,et al.  Convergence and asymptotic agreement in distributed decision problems , 1982, 1982 21st IEEE Conference on Decision and Control.

[27]  Nitin H. Vaidya,et al.  Distributed Learning with Adversarial Agents Under Relaxed Network Condition , 2019, ArXiv.

[28]  Nitin H. Vaidya,et al.  Robust Distributed Average Consensus via Exchange of Running Sums , 2016, IEEE Transactions on Automatic Control.

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

[30]  Nitin H. Vaidya,et al.  Asynchronous Non-Bayesian Learning in the Presence of Crash Failures , 2016, SSS.

[31]  Pooya Molavi,et al.  (Non-)Bayesian learning without recall , 2014, 53rd IEEE Conference on Decision and Control.