Abstract
In this paper, we consider distributed estimation problems where a set of agents are used for jointly estimating an interesting parameter from the noise measurements. By using the adaptation-then-combination rule in the traditional diffusion least mean square (DLMS), a DLMS is proposed by introducing a correction step with a gain factor between the adaptation and combination steps. An explicit expression for the network mean-square deviation is derived for the proposed algorithm, and a sufficient condition is established to guarantee the mean stability. Simulation results are provided to verify theoretical results, and it is shown that the proposed algorithm outperforms the traditional DLMS.
Similar content being viewed by others
References
R. Abdolee, B. Champagne, A.H. Sayed, A diffusion LMS strategy for parameter estimation in noisy regressor applications, in 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO), Bucharest, pp. 749–753 (2012)
P. Braca, S. Marano, V. Matta, Running consensus in wireless sensor networks, in Proceedings of the IEEE International Conference on Information Fusion, Cologne, Germany, p. 1C6 (2008)
F.S. Cattivelli, A.H. Sayed, Diffusion LMS strategies for distributed estimation. IEEE Trans. Signal Process. 58(3), 1035–1048 (2010)
B. Chen, L. Xing, N. Zheng, J.C. Prncipe, Quantized minimum error entropy criterion. IEEE Trans. Neural Netw. Learn. Syst. 30(5), 1370–1380 (2019)
J. Chen, A.H. Sayed, Diffusion adaptation strategies for distributed optimization and learning over networks. IEEE Trans. Signal Process. 60(8), 4289C4305 (2012)
J. Chen, A.H. Sayed, On the learning behavior of adaptive networks part I: transient analysis. IEEE Trans. Inf. Theory 61(6), 3487C3517 (2015)
J. Chen, A.H. Sayed, On the learning behavior of adaptive networks part II: performance analysis. IEEE Trans. Inf. Theory 61(6), 3518C3548 (2015)
R.H. Koning, H. Neudecker, T. Wansbeek, Block Kronecker products and the vecb operator. Linear Algebra Appl. 149, 165–184 (1991)
J. Lee, S.E. Kim, W.J. Song, Data-selective diffusion LMS for reducing communication overhead. Signal Process. 113(7), 211–217 (2015)
Y. Liu, C. Li, Secure distributed estimation over wireless sensor networks under attacks. IEEE Trans. Aerosp. Electron. Syst. 54(4), 1815–1831 (2018)
C.G. Lopes, A.H. Sayed, Diffusion least-mean squares over adaptive networks: formulation and performance analysis. IEEE Trans. Signal Process. 56(7), 31223136 (2008)
L. Lu, H. Zhao, W. Wang, Y. Yu, Performance analysis of the robust diffusion normalized least mean \({p} \)-power algorithm. IEEE Trans. Circuits Syst. II Express Briefs 65(12), 2047–2051 (2018)
L. Lu, Z. Zheng, B. Champagne, X. Yang, W. Wu, Self-regularized nonlinear diffusion algorithm based on levenberg gradient descent. Signal Process. 163, 107–114 (2019)
L. Lu, H. Zhao, B. Champagne, Diffusion total least-squares algorithm with multi-node feedback. Signal Process. 153, 243–254 (2018)
R. Mohammadloo, G. Azarnia, M. A. Tinati, Increasing the initial convergence of distributed diffusion LMS algorithm by a new variable tap-length variable step-size method, in 21st Iranian Conference on Electrical Engineering (ICEE), Mashhad, pp. 1–5 (2013)
R. Nassif, C. Richard, A. Ferrari, A.H. Sayed, Diffusion LMS for multitask problems with local linear equality constraints. IEEE Trans. Signal Process. 65(19), 4979–4993 (2017)
R. Olfati-Saber, J.S. Shamma, Consensus filters for sensor networks and distributed sensor fusion, in Proceedings of IEEE Conference on Decision and Control (CDC). IEEE, p. 66986703 (2005)
M. Omer Bin Saeed, A. Zerguine, S.A. Zummo, Variable step-size least mean square algorithms over adaptive networks, in 10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010), Kuala Lumpur, pp. 381–384 (2010)
S. Sardellitti, M. Giona, S. Barbarossa, Fast distributed average consensus algorithms based on advection-diffusion processes. IEEE Trans. Signal Process. 58(2), 826842 (2010)
A.H. Sayed, Diffusion strategies for adaptation and learning over networks. IEEE Signal Process. Mag. 30(3), 155–171 (2013)
A.H. Sayed, Fundamentals of Adaptive Filtering (Wiley, New York, 2003)
A.H. Sayed, Adaptive networks, in Proceedings of the IEEE, vol. 102, no. 4, p. 460C497 (2014)
A.H. Sayed, Adaptation, learning, and optimization over networks. Found. Trends Mach. Learn. 7(4–5), 311C801 (2014)
N. Takahashi, I. Yamada, A.H. Sayed, Diffusion least-mean squares with adaptive combiners: formulation and performance analysis. IEEE Trans. Signal Process. 58(9), 4795–4810 (2010)
K. Yuan, Q. Ling, W. Yin, On the convergence of decentralized gradient descent. SIAM J. Optim. 26(3), 1835C1854 (2016)
K. Yuan, B. Ying, X. Zhao, A.H. Sayed, Exact diffusion for distributed optimization and learning-part I: algorithm development. IEEE Trans. Signal Process. 67(3), 708–723 (2019)
K. Yuan, B. Ying, X. Zhao, A.H. Sayed, Exact diffusion for distributed optimization and learning-part II: convergence analysis. IEEE Trans. Signal Process. 67(3), 724–739 (2019)
Acknowledgements
This work was supported by National Key R&D Program of China (2018YFB1402600) and NSFC (61976013).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chang, H., Li, W. Correction-Based Diffusion LMS Algorithms for Distributed Estimation. Circuits Syst Signal Process 39, 4136–4154 (2020). https://doi.org/10.1007/s00034-020-01363-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-020-01363-4