Zhongguo Li,
Zhongguo (Department of Computer Science, University College London, UK) Li,
Zhengtao Ding,
Zhengtao (Department of Electrical and Electronic Engineering, University of Manchester, UK) Ding
e.a.
Elsevier Science
e druk, 2024
9780443216367
Distributed Optimization and Learning
A Control-Theoretic Perspective
Specificaties
Paperback, blz.
|
Engels
Elsevier Science |
e druk, 2024
ISBN13: 9780443216367
Rubricering
Verwachte levertijd ongeveer 9 werkdagen
Samenvatting
Distributed Optimization and Learning: A Control-Theoretic Perspective illustrates the underlying principles of distributed optimization and learning. The book presents a systematic and self-contained description of distributed optimization and learning algorithms from a control-theoretic perspective. It focuses on exploring control-theoretic approaches and how those approaches can be utilized to solve distributed optimization and learning problems over network-connected, multi-agent systems. As there are strong links between optimization and learning, this book provides a unified platform for understanding distributed optimization and learning algorithms for different purposes.
Specificaties
Inhoudsopgave
<p>Part I. Fundamental Concepts and Algorithms<br>1. Introduction to distributed optimisation and learning<br>2. A control perspective to single agent optimisation<br>3. Centralised optimisation and learning<br>4. Distributed frameworks. consensus, optimisation and learning<br>5. Distributed unconstrained optimisation<br>6. Constrained optimisation for resource allocation<br>7. Non-cooperative optimisation<br> <br>Part II. Advanced Algorithms and Applications<br>8. Output regulation to time-varying optimisation<br>9. Adaptive control to optimisation over directed graphs<br>10. Event-triggered control to optimal coordination<br>11. Fixed-time control to cooperative and competitive optimisation<br>12. Robust and adaptive control to competitive optimisation<br>13. Surrogate-model assisted algorithms to distributed optimisation<br>14. Discrete-time algorithms for supervised learning<br>15. Discrete-time output regulation for optimal robot coordination</p>