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.
Table of Contents
Part I. Fundamental Concepts and Algorithms 1. Introduction to distributed optimisation and learning 2. A control perspective to single agent optimisation 3. Centralised optimisation and learning 4. Distributed frameworks. consensus, optimisation and learning 5. Distributed unconstrained optimisation 6. Constrained optimisation for resource allocation 7. Non-cooperative optimisation Part II. Advanced Algorithms and Applications 8. Output regulation to time-varying optimisation 9. Adaptive control to optimisation over directed graphs 10. Event-triggered control to optimal coordination 11. Fixed-time control to cooperative and competitive optimisation 12. Robust and adaptive control to competitive optimisation 13. Surrogate-model assisted algorithms to distributed optimisation 14. Discrete-time algorithms for supervised learning 15. Discrete-time output regulation for optimal robot coordination