Stochastic Incremental Gradient Descent for Estimation in Sensor Networks

Ram, S. Sundhar; Nedić, Angelia; Veeravalli, Venugopal V.

doi:10.1109/acssc.2007.4487280

Cited by 46 publications

(42 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diffusion Kalman filtering and smoothing algorithms were also proposed [10], [11], [32]. Distributed estimation algorithms based on incremental [3], [5], [12] and consensus strategies [13]- [15] have also been proposed. The work [14] proposes a distributed LMS algorithm based on consensus techniques that relies on node hierarchy to reduce communications.…”

Section: Introductionmentioning

confidence: 98%

Diffusion LMS Strategies for Distributed Estimation

Cattivelli

Sayed

2010

IEEE Trans. Signal Process.

1,061

1,021

View full text Add to dashboard Cite

We consider the problem of distributed estimation, where a set of nodes is required to collectively estimate some parameter of interest from noisy measurements. The problem is useful in several contexts including wireless and sensor networks, where scalability, robustness, and low power consumption are desirable features. Diffusion cooperation schemes have been shown to provide good performance, robustness to node and link failure, and are amenable to distributed implementations. In this work we focus on diffusion-based adaptive solutions of the LMS type. We motivate and propose new versions of the diffusion LMS algorithm that outperform previous solutions. We provide performance and convergence analysis of the proposed algorithms, together with simulation results comparing with existing techniques. We also discuss optimization schemes to design the diffusion LMS weights.

show abstract

Section: Introductionmentioning

confidence: 98%

Diffusion LMS Strategies for Distributed Estimation

Cattivelli

Sayed

2010

IEEE Trans. Signal Process.

1,061

1,021

View full text Add to dashboard Cite

show abstract

“…Minimizing a sum of convex functions, where each component is known only to a particular node, has attracted much attention recently, due to its simple formulation and wide applications [22], [20], [21], [26], [27], [23], [31], [30], [28], [29], [32], [25], [24]. The key idea is that properly designed distributed control protocols or computation algorithms can lead to a collective optimization, based on simple exchanged information and individual optimum observation.…”

Section: Introductionmentioning

confidence: 99%

“…The key idea is that properly designed distributed control protocols or computation algorithms can lead to a collective optimization, based on simple exchanged information and individual optimum observation. Subgradient-based incremental methods were established via deterministic or randomized iteration, where each node is assumed to be able to compute a local subgradient value of its objective function [20], [21], [26], [22], [25], [24]. Non-subgradientbased methods also showed up in the literature.…”

Section: Introductionmentioning

confidence: 99%

Reaching optimal consensus for multi-agent systems based on approximate projection

Lou

Shi

Johansson

et al. 2012

Proceedings of the 10th World Congress on Intelligent Control and Automation

View full text Add to dashboard Cite

Abstract-In this paper, we propose an approximately projected consensus algorithm for a multi-agent system to cooperatively compute the intersection of several convex sets, each of which is known only to a particular node. Instead of assuming the exact convex projection, we allow each node to just compute an approximate projection. The communication graph is directed and time-varying, and nodes can only exchange information via averaging among local view. We present sufficient and/or necessary conditions for the considered algorithm on how much projection accuracy is required to ensure a global consensus within the intersection set, under the assumption that the communication graph is uniformly jointly strongly connected. A numerical example indicates that the approximately projected consensus algorithm achieves better performance than the exact projected consensus algorithm. The results add the understanding of the fundamentals of distributed convex intersection computation.

show abstract

“…For example, the ring-network structure has been considered [86][87][88] for in-network information processing, where the sensors are organized in a cycle and process the information by passing the estimates along the cycle. Consensus-based approaches for distributed estimation have been discussed [14,[89][90][91][92].…”

Section: (H) Distributed Parameter Estimationmentioning

confidence: 99%

Distributed inference in wireless sensor networks

Veeravalli

Varshney

2012

Phil. Trans. R. Soc. A.

110

View full text Add to dashboard Cite

Statistical inference is a mature research area, but distributed inference problems that arise in the context of modern wireless sensor networks (WSNs) have new and unique features that have revitalized research in this area in recent years. The goal of this paper is to introduce the readers to these novel features and to summarize recent research developments in this area. In particular, results on distributed detection, parameter estimation and tracking in WSNs will be discussed, with a special emphasis on solutions to these inference problems that take into account the communication network connecting the sensors and the resource constraints at the sensors.

show abstract

Stochastic Incremental Gradient Descent for Estimation in Sensor Networks

Cited by 46 publications

References 10 publications

Diffusion LMS Strategies for Distributed Estimation

Diffusion LMS Strategies for Distributed Estimation

Reaching optimal consensus for multi-agent systems based on approximate projection

Distributed inference in wireless sensor networks

Contact Info

Product

Resources

About