Abstract

This paper considers the problem of distributed adaptive linear parameter estimation in multiagent inference networks. Local sensing model information is only partially available at the agents, and interagent communication is assumed to be unpredictable. The paper develops a generic mixed time-scale stochastic procedure consisting of simultaneous distributed learning and estimation, in which the agents adaptively assess their relative observation quality over time and fuse the innovations accordingly. Under rather weak assumptions on the statistical model and the interagent communication, it is shown that, by properly tuning the consensus potential with respect to the innovation potential, the asymptotic information rate loss incurred in the learning process may be made negligible. As such, it is shown that the agent estimates are asymptotically efficient, in that their asymptotic covariance coincides with that of a centralized estimator (the inverse of the centralized Fisher information rate for Gaussian systems) with perfect global model information and having access to all observations at all times. The proof techniques are mainly based on convergence arguments for non-Markovian mixed time-scale stochastic approximation procedures. Several approximation results developed in the process are of independent interest.

Keywords

  1. multiagent systems
  2. distributed estimation
  3. mixed time-scale
  4. stochastic approximation
  5. asymptotically efficient
  6. adaptive algorithms

MSC codes

  1. 93E10
  2. 93E35
  3. 60G35
  4. 94A13
  5. 62M09
  6. 62M05

Get full access to this article

View all available purchase options and get full access to this article.

References

1.
D. Bertsekas, J. Tsitsiklis, and M. Athans, Convergence Theories of Distributed Iterative Processes: A Survey, Technical report, Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, 1984.
2.
P. Billingsley, Convergence of Probability Measures, John Wiley and Sons, New York, 1999.
3.
V. S. Borkar, Stochastic Approximation: A Dynamical Systems Viewpoint, Cambridge University Press, Cambridge, UK, 2008.
4.
S. Boyd, A. Ghosh, B. Prabhakar, and D. Shah, Randomized gossip algorithms, IEEE Trans. Inform. Theory, 52 (2006), pp. 2508--2530.
5.
R. Carli, A. Chiuso, L. Schenato, and S. Zampieri, Distributed Kalman filtering using consensus strategies, in Proceedings of the 46th IEEE Conference on Decision and Control, New Orleans, LA, 2007, pp. 5486--5491.
6.
F. R. K. Chung, Spectral Graph Theory, AMS, Providence, RI, 1997.
7.
T. Chung, V. Gupta, J. Burdick, and R. Murray, On a decentralized active sensing strategy using mobile sensor platforms in a network, in Proceedings of the 43rd IEEE Conference on Decision and Control, Vol. 2, Paradise Island, Bahamas, 2004, pp. 1914--1919.
8.
A. G. Dimakis, S. Kar, J. Moura, M. G. Rabbat, and A. Scaglione, Gossip algorithms for distributed signal processing, Proc. IEEE, 98 (2010), pp. 1847--1864.
9.
L. E. Dubins and D. A. Freedman, A sharper form of the Borel-Cantelli lemma and the strong law, Ann. Math. Statist., 36 (1965), pp. 800--807.
10.
V. Fabian, Stochastic approximation of minima with improved asymptotic speed, Ann. Math. Statist., 37 (1967), pp. 191--200.
11.
V. Fabian, On asymptotic normality in stochastic approximation, Ann. Math. Statist., 39 (1968), pp. 1327--1332.
12.
S. B. Gelfand and S. K. Mitter, Recursive stochastic algorithms for global optimization in $\mathbb{R}^d$, SIAM J. Control Optim., 29 (1991), pp. 999--1018.
13.
P. R. Halmos, Measure Theory, Springer-Verlag, New York, 1974.
14.
M. Huang and J. Manton, Stochastic approximation for consensus seeking: Mean square and almost sure convergence, in Proceedings of the 46th IEEE Conference on Decision and Control, New Orleans, LA, 2007.
15.
A. Jadbabaie, A. Tahbaz-Salehi, and A. Sandroni, Non-Bayesian Social Learning, PIER working paper 2010-005, University of Pennsylvania, Philadelphia, Feb., 2010.
16.
D. Jakovetic, J. Xavier, and J. Moura, Weight optimization for consenus algorithms with correlated switching topology, IEEE Trans. Signal Process., 58 (2010), pp. 3788--3801.
17.
D. Jakovetic, J. Xavier, and J. Moura, Cooperative convex optimization in networked systems: Augmented Lagrangian algorithms with directed gossip communication, IEEE Trans. Signal Process., 59 (2011), pp. 3889--3902.
18.
S. Kar, J. M. F. Moura, and K. Ramanan, Distributed parameter estimation in sensor networks: Nonlinear observation models and imperfect communication, IEEE Trans. Inform. Theory, 58 (2012), pp. 3575--3605.
19.
S. Kar and J. M. F. Moura, Distributed consensus algorithms in sensor networks with imperfect communication: Link failures and channel noise, IEEE Trans. Signal Process., 57 (2009), pp. 355--369.
20.
S. Kar and J. Moura, Convergence rate analysis of distributed gossip (linear parameter) estimation: Fundamental limits and tradeoffs, IEEE J. Selected Topics Signal Process., 5 (2011), pp. 674--690.
21.
U. A. Khan and J. M. F. Moura, Distributing the Kalman filter for large-scale systems, IEEE Trans. Signal Process., 56 (2008), pp. 4919--4935.
22.
V. Krishnamurthy, K. Topley, and G. Yin, Consensus formation in a two-time-scale Markovian system, Multiscale Model. Simul., 7 (2009), pp. 1898--1927.
23.
H. Kushner and G. Yin, Asymptotic properties of distributed and communicating stochastic approximation algorithms, SIAM J. Control Optim., 25 (1987), pp. 1266--1290.
24.
T. L. Lai and C. Z. Wei, Asymptotically efficient self-tuning regulators, SIAM J. Control Optim., 25 (1987), pp. 466--481.
25.
T. L. Lai, Asymptotic properties of nonlinear least squares estimates in stochastic regression models, Ann. Statist., 2 (1994), pp. 1917--1930.
26.
K. Li and J. Baillieul, Robust and efficient quantization and coding for control of multidimensional linear systems under data rate constraints, Internat. J. Robust Nonlinear Control, 17 (2007), pp. 898--920.
27.
T. Li, M. Fu, L. Xie, and J.-F. Zhang, Distributed consensus with limited communication data rate, IEEE Trans. Automat. Control, 56 (2011), pp. 279--292.
28.
I. Lobel and A. Ozdaglar, Distributed subgradient methods for convex optimization over random networks, IEEE Trans. Automat. Control, 56 (2011), pp. 1291--1306.
29.
C. Lopes and A. Sayed, Diffusion least-mean squares over adaptive networks: Formulation and performance analysis, IEEE Trans. Signal Process., 56 (2008), pp. 3122--3136.
30.
A. Matveev and A. Savkin, The problem of state estimation via asynchronous communication channels with irregular transmission times, IEEE Trans. Automat. Control, 48 (2006), pp. 670--676.
31.
M. Nevel'son and R. Has'minskii, Stochastic Approximation and Recursive Estimation, AMS, Providence, RI, 1973.
32.
R. Olfati-Saber, J. A. Fax, and R. M. Murray, Consensus and cooperation in networked multi-agent systems, Proc. IEEE, 95 (2007), pp. 215--233.
33.
R. Olfati-Saber, Kalman-consensus filter: Optimality, stability, and performance, in Proceedings of the 48th IEEE Conference on Decision and Control, Shanghai, China, 2009, pp. 7036--7042.
34.
B. Polyak, Introduction to Optimization, Optimization Software, New York, 1987.
35.
S. S. Ram, A. Nedic, and V. V. Veeravalli, Incremental stochastic subgradient algorithms for convex optimization, SIAM J. Optim., 20 (2009), pp. 691--717.
36.
I. D. Schizas, A. Ribeiro, and G. B. Giannakis, Consensus in ad hoc WSNs with noisy links---Part I: Distributed estimation of deterministic signals, IEEE Trans. Signal Process., 56 (2008), pp. 350--364.
37.
I. Schizas, G. Mateos, and G. Giannakis, Stability analysis of the consensus-based distributed LMS algorithm, in Proceedings of the 33rd International Conference on Acoustics, Speech, and Signal Processing, Las Vegas, NV, 2008, pp. 3289--3292.
38.
S. Stankovic, M. Stankovic, and D. Stipanovic, Decentralized parameter estimation by consensus based stochastic approximation, in Proceedings of the 46th IEEE Conference on Decision and Control, New Orleans, LA, 2007, pp. 1535--1540.
39.
S. Tatikonda and S. Mitter, Control under communication constraints, IEEE Trans. Automat. Control, 49 (2004), pp. 1056--1068.
40.
J. N. Tsitsiklis, D. P. Bertsekas, and M. Athans, Distributed asynchronous deterministic and stochastic gradient optimization algorithms, IEEE Trans. Automat. Control, 31 (1986), pp. 803--812.
41.
L. Xiao, S. Boyd, and S. Lall, A scheme for robust distributed sensor fusion based on average consensus, in Proceedings of the International Conference on Information Processing in Sensor Networks, Los Angeles, CA, 2005, pp. 63--70.
42.
G. Yin, Y. Sun, and L. Wang, Asymptotic properties of consensus-type algorithms for networked systems with regime-switching topologies, Automatica, 47 (2011), pp. 1366--1378.
43.
G. Yin and Q. Zhang, Discrete-Time Markov Chains: Two-Time-Scale Methods and Applications, Springer, New York, 2005.

Information & Authors

Information

Published In

cover image SIAM Journal on Control and Optimization
SIAM Journal on Control and Optimization
Pages: 2200 - 2229
ISSN (online): 1095-7138

History

Submitted: 19 September 2011
Accepted: 22 January 2013
Published online: 28 May 2013

Keywords

  1. multiagent systems
  2. distributed estimation
  3. mixed time-scale
  4. stochastic approximation
  5. asymptotically efficient
  6. adaptive algorithms

MSC codes

  1. 93E10
  2. 93E35
  3. 60G35
  4. 94A13
  5. 62M09
  6. 62M05

Authors

Affiliations

Metrics & Citations

Metrics

Citations

If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.

Cited By

View Options

View options

PDF

View PDF

Media

Figures

Other

Tables

Share

Share

Copy the content Link

Share with email

Email a colleague

Share on social media

The SIAM Publications Library now uses SIAM Single Sign-On for individuals. If you do not have existing SIAM credentials, create your SIAM account https://my.siam.org.