Foundations and Trends® in Machine Learning > Vol 7 > Issue 4-5

Adaptation, Learning, and Optimization over Networks

By Ali H. Sayed, University of California, Los Angeles, USA, sayed@ee.ucla.edu

 
Suggested Citation
Ali H. Sayed (2014), "Adaptation, Learning, and Optimization over Networks", Foundations and Trends® in Machine Learning: Vol. 7: No. 4-5, pp 311-801. http://dx.doi.org/10.1561/2200000051

Publication Date: 25 Jul 2014
© 2014 A. H. Sayed
 
Subjects
Adaptive control and signal processing,  Behavioral, cognitive and neural learning,  Data mining,  Graphical models,  Online learning,  Optimization,  Statistical learning theory,  Computational learning,  Distributed computing,  Detection and estimation,  Pattern recognition and learning,  Signal processing for communications,  Control/Graph-theoretic models,  Dynamics and asymptotic behavior of networks,  Adaptive signal processing,  Distributed and network signal processing,  Statistical/Machine learning,  Statistical signal processing,  Stochastic networks,  Stochastic optimization,  Control of multi-agent systems
 
Keywords
Multi-agent learningMulti-agent optimizationMulti-agent adaptationDistributed optimizationAdaptive networksDiffusion strategiesConsensus strategiesIncremental strategiesStochastic-gradient algorithmsDistributed stochastic-gradient algorithmsFusion-based processingCentralized processingCooperative processingGossip strategiesConstrained optimization
 

Free Preview:

Download extract

Share

Download article
In this article:
1. Motivation and Notation 
2. Optimization by Single Agents 
3. Stochastic Optimization by Single Agents 
4. Performance of Single Agents 
5. Centralized Adaptation and Learning 
6. Multi-Agent Network Model 
7. Multi-Agent Distributed Strategies 
8. Evolution of Multi-Agent Networks 
9. Stability of Multi-Agent Networks 
10. Long-Term Network Dynamics 
11. Performance of Multi-Agent Networks 
12. Benefits of Cooperation 
13. Role of Informed Agents 
14. Combination Policies 
15. Extensions and Conclusions 
Acknowledgements 
Appendices 
References 

Abstract

This work deals with the topic of information processing over graphs. The presentation is largely self-contained and covers results that relate to the analysis and design of multi-agent networks for the distributed solution of optimization, adaptation, and learning problems from streaming data through localized interactions among agents. The results derived in this work are useful in comparing network topologies against each other, and in comparing networked solutions against centralized or batch implementations. There are many good reasons for the peaked interest in distributed implementations, especially in this day and age when the word “network” has become commonplace whether one is referring to social networks, power networks, transportation networks, biological networks, or other types of networks. Some of these reasons have to do with the benefits of cooperation in terms of improved performance and improved resilience to failure. Other reasons deal with privacy and secrecy considerations where agents may not be comfortable sharing their data with remote fusion centers. In other situations, the data may already be available in dispersed locations, as happens with cloud computing. One may also be interested in learning through data mining from big data sets. Motivated by these considerations, this work examines the limits of performance of distributed solutions and discusses procedures that help bring forth their potential more fully. The presentation adopts a useful statistical framework and derives performance results that elucidate the mean-square stability, convergence, and steady-state behavior of the learning networks. At the same time, the work illustrates how distributed processing over graphs gives rise to some revealing phenomena due to the coupling effect among the agents. These phenomena are discussed in the context of adaptive networks, along with examples from a variety of areas including distributed sensing, intrusion detection, distributed estimation, online adaptation, network system theory, and machine learning.

DOI:10.1561/2200000051
ISBN: 978-1-60198-850-8
518 pp. $99.00
Buy book (pb)
 
ISBN: 978-1-60198-851-5
518 pp. $240.00
Buy E-book (.pdf)
Table of contents:
1. Motivation and Notation
2. Optimization by Single Agents
3. Stochastic Optimization by Single Agents
4. Performance of Single Agents
5. Centralized Adaptation and Learning
6. Multi-Agent Network Model
7. Multi-Agent Distributed Strategies
8. Evolution of Multi-Agent Networks
9. Stability of Multi-Agent Networks
10. Long-Term Network Dynamics
11. Performance of Multi-Agent Networks
12. Benefits of Cooperation
13. Role of Informed Agents
14. Combination Policies
15. Extensions and Conclusions
Acknowledgements
Appendices
References

Adaptation, Learning, and Optimization over Networks

Adaptation, Learning, and Optimization over Networks deals with the topic of information processing over graphs. The presentation is largely self-contained and covers results that relate to the analysis and design of multi-agent networks for the distributed solution of optimization, adaptation, and learning problems from streaming data through localized interactions among agents. The results derived in this monograph are useful in comparing network topologies against each other, and in comparing networked solutions against centralized or batch implementations.

There are many good reasons for the peaked interest in distributed implementations, especially in this day and age when the word “network” has become commonplace whether one is referring to social networks, power networks, transportation networks, biological networks, or other types of networks. Some of these reasons have to do with the benefits of cooperation in terms of improved performance and improved resilience to failure. Other reasons deal with privacy and secrecy considerations where agents may not be comfortable sharing their data with remote fusion centers. In other situations, the data may already be available in dispersed locations, as happens with cloud computing. One may also be interested in learning through data mining from big data sets. Motivated by these considerations, Adaptation, Learning, and Optimization over Networks examines the limits of performance of distributed solutions and discusses procedures that help bring forth their potential more fully.

Adaptation, Learning, and Optimization over Networks adopts a useful statistical framework and derives performance results that elucidate the mean-square stability, convergence, and steady-state behavior of the learning networks. At the same time, the monograph illustrates how distributed processing over graphs gives rise to some revealing phenomena due to the coupling effect among the agents. These phenomena are discussed in the context of adaptive networks, along with examples from a variety of areas including distributed sensing, intrusion detection, distributed estimation, online adaptation, network system theory, and machine learning.

 
MAL-051