Asymptotically Efficient Distributed Estimation With Exponential Family Statistics

This paper studies the problem of distributed parameter estimation in multiagent networks with exponential family observation statistics. A certainty-equivalence type distributed estimator of the consensus-plus-innovations form is proposed in which, at each observation sampling epoch, agents update their local parameter estimates by appropriately combining the data received from their neighbors and the locally sensed new information (innovation). Under global observability of the networked sensing model, i.e., the ability to distinguish between different instances of the parameter value based on the joint observation statistics, and mean connectivity of the inter-agent communication network, the proposed estimator is shown to yield consistent parameter estimates at each network agent. Further, it is shown that the distributed estimator is asymptotically efficient, in that, the asymptotic covariances of the agent estimates coincide with that of the optimal centralized estimator, i.e., the inverse of the centralized Fisher information rate. From a technical viewpoint, the proposed distributed estimator leads to non-Markovian mixed time-scale stochastic recursions and the analytical methods developed in this paper contribute to the general theory of distributed stochastic approximation.

[1]  Gang George Yin,et al.  Consensus Formation in a Two-Time-Scale Markovian System , 2009, Multiscale Model. Simul..

[2]  Soummya Kar,et al.  Consensus + innovations distributed inference over networks: cooperation and sensing in networked systems , 2013, IEEE Signal Processing Magazine.

[3]  Srdjan S. Stankovic,et al.  Decentralized Parameter Estimation by Consensus Based Stochastic Approximation , 2007, IEEE Transactions on Automatic Control.

[4]  H. Vincent Poor,et al.  Distributed detection in noisy sensor networks , 2011, 2011 IEEE International Symposium on Information Theory Proceedings.

[5]  Soummya Kar,et al.  Distributed Parameter Estimation in Sensor Networks: Nonlinear Observation Models and Imperfect Communication , 2008, IEEE Transactions on Information Theory.

[6]  C. J. Stone,et al.  Adaptive Maximum Likelihood Estimators of a Location Parameter , 1975 .

[7]  S. Mitter,et al.  Recursive stochastic algorithms for global optimization in R d , 1991 .

[8]  T. Lai,et al.  Asymptotically efficient self-tuning regulators , 1987 .

[9]  V. Fabian.  On Asymptotically Efficient Recursive Estimation , 1978 .

[10]  L. Brown.  Fundamentals of statistical exponential families: with applications in statistical decision theory , 1986 .

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

[12]  John N. Tsitsiklis,et al.  Problems in decentralized decision making and computation , 1984 .

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

[14]  H. Vincent Poor,et al.  Bandit problems in networks: Asymptotically efficient distributed allocation rules , 2011, IEEE Conference on Decision and Control and European Control Conference.

[15]  Angelia Nedic,et al.  Distributed Stochastic Subgradient Projection Algorithms for Convex Optimization , 2008, J. Optim. Theory Appl..

[16]  Reza Olfati-Saber,et al.  Consensus and Cooperation in Networked Multi-Agent Systems , 2007, Proceedings of the IEEE.

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

[18]  Lihua Xie,et al.  Distributed Consensus With Limited Communication Data Rate , 2011, IEEE Transactions on Automatic Control.

[19]  José M. F. Moura,et al.  Distributed Detection via Gaussian Running Consensus: Large Deviations Asymptotic Analysis , 2011, IEEE Transactions on Signal Processing.

[20]  Ali H. Sayed,et al.  Diffusion Least-Mean Squares Over Adaptive Networks: Formulation and Performance Analysis , 2008, IEEE Transactions on Signal Processing.

[21]  Angelia Nedic,et al.  Distributed and Recursive Parameter Estimation in Parametrized Linear State-Space Models , 2008, IEEE Transactions on Automatic Control.

[22]  D. Sakrison.  Efficient recursive estimation; application to estimating the parameters of a covariance function , 1965 .

[23]  Ioannis D. Schizas,et al.  Stability analysis of the consensus-based distributed LMS algorithm , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[24]  Mikhail Borisovich Nevelʹson,et al.  Stochastic Approximation and Recursive Estimation , 1976 .

[25]  Soummya Kar,et al.  Convergence Rate Analysis of Distributed Gossip (Linear Parameter) Estimation: Fundamental Limits and Tradeoffs , 2010, IEEE Journal of Selected Topics in Signal Processing.

[26]  Ali H. Sayed,et al.  Diffusion Adaptation Strategies for Distributed Optimization and Learning Over Networks , 2011, IEEE Transactions on Signal Processing.

[27]  José M. F. Moura,et al.  Distributed Detection Over Noisy Networks: Large Deviations Analysis , 2011, IEEE Transactions on Signal Processing.

[28]  John N. Tsitsiklis,et al.  Convergence theories of distributed iterative processes: A survey , 1986 .

[29]  Tze Leung Lai,et al.  Asymptotic Properties of Nonlinear Least Squares Estimates in Stochastic Regression Models , 1994 .

[30]  V. Borkar.  Stochastic Approximation: A Dynamical Systems Viewpoint , 2008 .

[31]  V. Fabian.  Stochastic Approximation of Minima with Improved Asymptotic Speed , 1967 .

[32]  Andrew L. Rukhin,et al.  Recursive Testing of Multiple Hypotheses: Consistency and Efficiency of the Bayes Rule , 1994 .

[33]  G. Yin,et al.  Discrete-Time Markov Chains: Two-Time-Scale Methods and Applications , 2004 .

[34]  Soummya Kar,et al.  Distributed Consensus Algorithms in Sensor Networks With Imperfect Communication: Link Failures and Channel Noise , 2007, IEEE Transactions on Signal Processing.

[35]  U. Feige,et al.  Spectral Graph Theory , 2015 .

[36]  H. Vincent Poor,et al.  Distributed Linear Parameter Estimation: Asymptotically Efficient Adaptive Strategies , 2011, SIAM J. Control. Optim..

[37]  H. Kushner,et al.  Asymptotic properties of distributed and communication stochastic approximation algorithms , 1987 .

[38]  Jonathan H. Manton,et al.  Stochastic approximation for consensus seeking: Mean square and almost sure convergence , 2007, 2007 46th IEEE Conference on Decision and Control.

[39]  John N. Tsitsiklis,et al.  Distributed Asynchronous Deterministic and Stochastic Gradient Optimization Algorithms , 1984, 1984 American Control Conference.