Paper Info
Title
On the Learning Behavior of Adaptive Networks --- Part I: Transient Analysis
Abstract
This work carries out a detailed transient analysis of the learning behavior of multi-agent networks, and reveals interesting results about the learning abilities of distributed strategies. Among other results, the analysis reveals how combination policies influence the learning process of networked agents, and how these policies can steer the convergence point towards any of many possible Pareto optimal solutions. The results also establish that the learning process of an adaptive network undergoes three (rather than two) well-defined stages of evolution with distinctive convergence rates during the first two stages, while attaining a finite mean-square-error (MSE) level in the last stage. The analysis reveals what aspects of the network topology influence performance directly and suggests design procedures that can optimize performance by adjusting the relevant topology parameters. Interestingly, it is further shown that, in the adaptation regime, each agent in a sparsely connected network is able to achieve the same performance level as that of a centralized stochastic-gradient strategy even for left-stochastic combination strategies. These results lead to a deeper understanding and useful insights on the convergence behavior of coupled distributed learners. The results also lead to effective design mechanisms to help diffuse information more thoroughly over networks.
Year
DOI
Venue
2015
10.1109/TIT.2015.2427360
IEEE Transactions on Information Theory
Keywords
Field
DocType
multi-agent learning,pareto solutions,diffusion of information,distributed strategies,multi-agent adaptation
Convergence (routing),Mathematical optimization,Adaptive system,Computer science,Pareto optimal,Network topology,Distributed algorithm,Transient analysis
Journal
Volume
Issue
ISSN
PP
99
0018-9448
Citations 
PageRank 
References 
42
1.05
40
Authors
2
Name
Order
Citations
PageRank
Jianshu Chen188352.94
Ali H. Sayed29134667.71