Diffusion Strategies Outperform Consensus Strategies for Distributed Estimation Over Adaptive Networks

DOI10.1109/TSP.2012.2217338zbMATH Open1393.94465arXiv1205.3993MaRDI QIDQ4574175FDOQ4574175

Authors: Sheng-Yuan Tu, Ali H. Sayed 

Publication date: 18 July 2018

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Abstract: Adaptive networks consist of a collection of nodes with adaptation and learning abilities. The nodes interact with each other on a local level and diffuse information across the network to solve estimation and inference tasks in a distributed manner. In this work, we compare the mean-square performance of two main strategies for distributed estimation over networks: consensus strategies and diffusion strategies. The analysis in the paper confirms that under constant step-sizes, diffusion strategies allow information to diffuse more thoroughly through the network and this property has a favorable effect on the evolution of the network: diffusion networks are shown to converge faster and reach lower mean-square deviation than consensus networks, and their mean-square stability is insensitive to the choice of the combination weights. In contrast, and surprisingly, it is shown that consensus networks can become unstable even if all the individual nodes are stable and able to solve the estimation task on their own. When this occurs, cooperation over the network leads to a catastrophic failure of the estimation task. This phenomenon does not occur for diffusion networks: we show that stability of the individual nodes always ensures stability of the diffusion network irrespective of the combination topology. Simulation results support the theoretical findings.

Full work available at URL: https://arxiv.org/abs/1205.3993

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cited In (23)

• Diffusion-probabilistic least mean square algorithm
• Distributed adaptive consensus protocol with decaying gains
• Diffusion recursive least-squares for distributed estimation over adaptive networks
• Robust multitask diffusion affine projection M-estimate algorithm: design and performance analysis
• Adaptive clustering based on element-wised distance for distributed estimation over multi-task networks
• Distributed multi-task classification: a decentralized online learning approach
• Robust and scalable distributed recursive least squares
• Distributed cooperative wideband spectrum sensing algorithm based on subspace methods
• Adaptive multitask clustering algorithm based on distributed diffusion least-mean-square estimation
• Decentralized diffusion-based learning under non-parametric limited prior knowledge
• Diffusion least mean kurtosis algorithm and its performance analysis
• Diffusion-Based Adaptive Distributed Detection: Steady-State Performance in the Slow Adaptation Regime
• Distributed diffusion unscented Kalman filtering based on covariance intersection with intermittent measurements
• Adaptive Diffusion Schemes for Heterogeneous Networks
• Robust diffusion recursive least M-estimate adaptive filtering and its performance analysis
• Stochastic analysis of the diffusion least mean square and normalized least mean square algorithms for cyclostationary white Gaussian and non-Gaussian inputs
• Multi-agent reinforcement learning: a selective overview of theories and algorithms
• A Spatial Diffusion Strategy for Tap-Length Estimation Over Adaptive Networks
• A distributed diffusion Kalman filter with event‐triggered mechanism and guaranteed stability
• Diffusion bias-compensation RLS estimation over noisy node-specific networks
• Robust diffusion Huber-based normalized least mean square algorithm with adjustable thresholds
• A class of diffusion proportionate subband adaptive filters for sparse system identification over distributed networks
• Distributed algorithms for aggregative games on graphs

This page was built for publication: Diffusion Strategies Outperform Consensus Strategies for Distributed Estimation Over Adaptive Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4574175)