Distributed Learning for Cooperative Inference

We study the problem of cooperative inference where a group of agents interact over a network and seek to estimate a joint parameter that best explains a set of observations. Agents do not know the network topology or the observations of other agents. We explore a variational interpretation of the Bayesian posterior density, and its relation to the stochastic mirror descent algorithm, to propose a new distributed learning algorithm. We show that, under appropriate assumptions, the beliefs generated by the proposed algorithm concentrate around the true parameter exponentially fast. We provide explicit non-asymptotic bounds for the convergence rate. Moreover, we develop explicit and computationally efficient algorithms for observation models belonging to exponential families.

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

[2]  Judith Rousseau,et al.  Posterior concentration rates for infinite dimensional exponential families , 2012 .

[3]  L. Schmetterer.  Zeitschrift fur Wahrscheinlichkeitstheorie und Verwandte Gebiete. , 1963 .

[4]  Changzhi Wu,et al.  Stochastic mirror descent method for distributed multi-agent optimization , 2016, Optimization Letters.

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

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

[7]  Angelia Nedic,et al.  Distributed Gaussian learning over time-varying directed graphs , 2016, 2016 50th Asilomar Conference on Signals, Systems and Computers.

[8]  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).

[9]  Elchanan Mossel,et al.  Efficient Bayesian Learning in Social Networks with Gaussian Estimators , 2010, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[10]  Lucien Birg'e.  About the non-asymptotic behaviour of Bayes estimators , 2014 .

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

[13]  Yunmin Zhu,et al.  Optimal dimensionality reduction of sensor data in multisensor estimation fusion , 2005, IEEE Trans. Signal Process..

[14]  A. V. D. Vaart,et al.  Convergence rates of posterior distributions , 2000 .

[15]  Roger M. Cooke,et al.  Statistics in Expert Resolution: A Theory of Weights for Combining Expert Opinion , 1990 .

[16]  Pramod K. Varshney,et al.  Distributed detection with multiple sensors I. Fundamentals , 1997, Proc. IEEE.

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

[18]  Qipeng Liu,et al.  Non-Bayesian learning in social networks with time-varying weights , 2011, Proceedings of the 30th Chinese Control Conference.

[19]  A. Juditsky,et al.  Learning by mirror averaging , 2005, math/0511468.

[20]  V. Borkar,et al.  Asymptotic agreement in distributed estimation , 1982 .

[21]  B. O. Koopman.  On distributions admitting a sufficient statistic , 1936 .

[22]  Gustavo L. Gilardoni,et al.  On Reaching a Consensus Using Degroot's Iterative Pooling , 1993 .

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

[24]  Qipeng Liu,et al.  Distributed detection via Bayesian updates and consensus , 2014, 2015 34th Chinese Control Conference (CCC).

[25]  Marc Teboulle,et al.  Mirror descent and nonlinear projected subgradient methods for convex optimization , 2003, Oper. Res. Lett..

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

[27]  Nitin H. Vaidya,et al.  Asynchronous Distributed Hypothesis Testing in the Presence of Crash Failures , 2016, ArXiv.

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

[29]  Matthew J. Beal.  Variational algorithms for approximate Bayesian inference , 2003 .

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

[31]  Alex Olshevsky,et al.  Linear Time Average Consensus on Fixed Graphs and Implications for Decentralized Optimization and Multi-Agent Control , 2014, 1411.4186.

[32]  Angelia Nedic,et al.  On Stochastic Subgradient Mirror-Descent Algorithm with Weighted Averaging , 2013, SIAM J. Optim..

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

[34]  L. L. Cam,et al.  Asymptotic Methods In Statistical Decision Theory , 1986 .

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

[36]  Marco Dall'Aglio,et al.  Bayesian Posteriors Without Bayes' Theorem , 2012, ArXiv.

[37]  Christian Genest,et al.  Combining Probability Distributions: A Critique and an Annotated Bibliography , 1986 .

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

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

[40]  L. Lecam.  Convergence of Estimates Under Dimensionality Restrictions , 1973 .

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

[42]  Le Song,et al.  Scalable Bayesian Inference via Particle Mirror Descent , 2015, ArXiv.

[43]  John A. Gubner,et al.  Distributed estimation and quantization , 1993, IEEE Trans. Inf. Theory.

[44]  Le Song,et al.  Provable Bayesian Inference via Particle Mirror Descent , 2015, AISTATS.

[45]  Grace L. Yang,et al.  On Bayes Procedures , 1990 .

[46]  R. Karandikar,et al.  Sankhyā, The Indian Journal of Statistics , 2006 .

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

[48]  James A. Bucklew,et al.  Robust decentralized source localization via averaging , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[49]  Alexander Shapiro,et al.  Validation analysis of mirror descent stochastic approximation method , 2012, Math. Program..

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

[51]  Sergio Barbarossa,et al.  Distributed Detection and Estimation in Wireless Sensor Networks , 2013, ArXiv.

[52]  Michael G. Rabbat,et al.  Multi-agent mirror descent for decentralized stochastic optimization , 2015, 2015 IEEE 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).

[53]  Stephen G. Walker,et al.  Bayesian inference via a minimization rule , 2006 .

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

[55]  Stephen J. Roberts,et al.  A tutorial on variational Bayesian inference , 2012, Artificial Intelligence Review.

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

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

[58]  A. V. D. Vaart,et al.  Convergence rates of posterior distributions for non-i.i.d. observations , 2007, 0708.0491.

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

[60]  A. Zellner.  Optimal Information Processing and Bayes's Theorem , 1988 .

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

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

[63]  Subhashis Ghosal,et al.  A Review of Consistency and Convergence of Posterior Distribution , 2022 .

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

[65]  A. V. D. Vaart,et al.  CONVERGENCE RATES OF POSTERIOR DISTRIBUTIONS FOR NONIID OBSERVATIONS By , 2018 .

[66]  Shu-Li Sun,et al.  Multi-sensor optimal information fusion Kalman filter , 2004, Autom..

[67]  Polly S Nichols,et al.  Agreeing to disagree. , 2005, General dentistry.