Networked Signal and Information Processing: Learning by multiagent systems

被引：6

作者：

Vlaski, Stefan ^{[1
,2
]}

Kar, Soummya ^{[3
]}

Sayed, Ali H. ^{[4
,5
,6
,7
]}

Moura, Jose M. F. ^{[8
,9
,10
,11
,12
]}

机构：

[1] Imperial Coll, London SW7 2AZ, England

[2] Ecole Polytech Fed Lausanne, Adapt Syst Lab, Lausanne, Switzerland

[3] Princeton Univ, Elect Engn Dept, Princeton, NJ USA

[4] Ecole Polytech Fed Lausanne, CH-1015 Lausanne, Switzerland

[5] Univ Calif Los Angeles, Elect Engn, Los Angeles, CA USA

[6] US Natl Acad Engn, Washington, DC USA

[7] World Acad Sci, Trieste, Italy

[8] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA

[9] Amer Assoc Advancement Sci, Washington, DC USA

[10] Natl Acad Inventors, Tampa, FL USA

[11] Portugal Acad Sci, Lisbon, Portugal

[12] Natl Acad Engn, New Delhi, India

来源：

IEEE SIGNAL PROCESSING MAGAZINE | 2023年 / 40卷 / 05期

关键词：

Privacy; Protocols; Network topology; Scalability; Signal processing algorithms; Information processing; Robustness; DISTRIBUTED CONSENSUS ALGORITHMS; PART I; SENSOR NETWORKS; ADAPTIVE NETWORKS; LARGE-SCALE; OPTIMIZATION; DIFFUSION; CONVERGENCE; PERFORMANCE; STABILITY;

D O I：

10.1109/MSP.2023.3267896

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This article reviews significant advances in networked signal and information processing (SIP), which have enabled in the last 25 years extending decision making and inference, optimization, control, and learning to the increasingly ubiquitous environments of distributed agents. As these interacting agents cooperate, new collective behaviors emerge from local decisions and actions. Moreover, and significantly, theory and applications show that networked agents, through cooperation and sharing, are able to match the performance of cloud or federated solutions while offering the potential for improved privacy, increased resilience, and conserved resources. A longer version of this manuscript, with examples and illustrative applications, is available at https://arxiv.org/abs/2210.13767.

引用

页码：92 / 105

页数：14

共 60 条

[1] Large Deviations Performance of Consensus plus Innovations Distributed Detection With Non-Gaussian Observations
Bajovic, Dragana
Jakovetic, Dusan
Moura, Jose M. F.
Xavier, Joao
Sinopoli, Bruno
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2012, 60 (11) : 5987 - 6002
[2] Decentralized maximum-likelihood estimation for sensor networks composed of nonlinearly coupled dynamical systems
Barbarossa, Sergio
Scutari, Gesualdo
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2007, 55 (07) : 3456 - 3470
[3] A NECESSARY AND SUFFICIENT CONDITION FOR REACHING A CONSENSUS USING DEGROOT METHOD
BERGER, RL
[J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1981, 76 (374) : 415 - 418
[4] Distributed optimization and statistical learning via the alternating direction method of multipliers
Boyd S.
Parikh N.
Chu E.
Peleato B.
Eckstein J.
[J]. Foundations and Trends in Machine Learning, 2010, 3 (01): : 1 - 122
[5] Randomized gossip algorithms
Boyd, Stephen
Ghosh, Arpita
Prabhakar, Balaji
Shah, Devavrat
[J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (06) : 2508 - 2530
[6] Braca P., 2008, INFORM FUSION 2008 1, P1
[7] Diffusion recursive least-squares for distributed estimation over adaptive networks
Cattivelli, Federico S.
Lopes, Cassio G.
Sayed, Ali. H.
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2008, 56 (05) : 1865 - 1877
[8] Diffusion Strategies for Distributed Kalman Filtering and Smoothing
Cattivelli, Federico S.
Sayed, Ali H.
[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2010, 55 (09) : 2069 - 2084
[9] Diffusion LMS Strategies for Distributed Estimation
Cattivelli, Federico S.
Sayed, Ali H.
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2010, 58 (03) : 1035 - 1048
[10] On the Learning Behavior of Adaptive Networks-Part I: Transient Analysis
Chen, Jianshu
Sayed, Ali H.
[J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2015, 61 (06) : 3487 - 3517

← 1 2 3 4 5 6 →