Distributed Optimization and Learning

A Control-Theoretic Perspective

1st Edition - July 18, 2024
Authors: Zhongguo Li, Zhengtao Ding
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 2 1 6 3 6 - 7
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 2 1 6 3 7 - 4

Distributed Optimization and Learning: A Control-Theoretic Perspective illustrates the underlying principles of distributed optimization and learning. The book presents a systemati… Read more

Purchase options

LIMITED OFFER

Save 50% on book bundles

Immediately download your ebook while waiting for your print delivery. No promo code needed.

Institutional subscription on ScienceDirect

Request a sales quote

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.

Cover image
Title page
Table of Contents
Copyright
Dedication
Biography
Zhongguo Li
Zhengtao Ding
Preface
Part I: Fundamental concepts and algorithms
Chapter 1: Introduction to distributed optimization and learning
Abstract
1.1. Background
1.2. Literature review
1.3. Book organization
Bibliography
Chapter 2: Control perspective to single agent optimization
Abstract
2.1. Unconstrained optimization
2.2. Set constrained optimization
2.3. Optimization with affine constraints
2.4. Discrete-time control perspective to optimization
Bibliography
Chapter 3: Distributed frameworks: Graphs, consensus, optimization, and learning
Abstract
3.1. Centralized networks: Structures and limitations
3.2. Centralized optimization and learning
3.3. Graph theory
3.4. Fundamental consensus algorithms
3.5. Preliminary lemmas
Bibliography
Chapter 4: Distributed unconstrained optimization
Abstract
4.1. Introduction to distributed unconstrained optimization
4.2. Problem formulation
4.3. Algorithm design and convergence analysis
Bibliography
Chapter 5: Distributed constrained optimization for resource allocation
Abstract
5.1. Introduction
5.2. Problem formulation
5.3. Algorithm design and convergence analysis
Bibliography
Chapter 6: Non-cooperative optimization
Abstract
6.1. Nash equilibrium problem
6.2. Game formulation on networks
6.3. Distributed gossip-based algorithm design
6.4. Convergence analysis
6.5. Simulation results
Bibliography
Part II: Advanced algorithms and applications
Chapter 7: Output regulation to time-varying optimization
Abstract
7.1. Introduction
7.2. Problem formulation
7.3. Preliminaries
7.4. Distributed Optimization Algorithm I
7.5. Distributed Optimization Algorithm II
7.6. Simulation studies
7.7. Summary
Bibliography
Chapter 8: Adaptive approach to optimization
Abstract
8.1. Adaptive preference formulation for cooperative multi-objective resource allocation
8.2. Adaptive again design for non-cooperative Nash equilibrium seeking
Bibliography
Chapter 9: Fixed-time control to optimization
Abstract
9.1. Time-varying multi-objective optimization
9.2. Fixed-time Nash equilibrium searching
Bibliography
Chapter 10: Surrogate-assisted algorithms to distributed optimization
Abstract
10.1. Introduction
10.2. Problem formulation
10.3. Main results
10.4. Simulation study
10.5. Summary
Bibliography
Chapter 11: Discrete-time algorithms to supervised learning
Abstract
11.1. Introduction
11.2. Problem formulation and algorithm development
11.3. Performance analysis
11.4. Simulation and discussion
11.5. Summary
Bibliography
Chapter 12: Game theory-based distributed algorithm for electricity market
Abstract
12.1. Introduction
12.2. Problem formulation
12.3. Distributed Nash equilibrium seeking algorithm
12.4. Case studies
12.5. Summary
Bibliography
Bibliography
Bibliography
Index

Zhongguo Li

Zhongguo Li is a lecturer in robotics and AI at the Department of Computer Science, University College London, in the U.K. His research interests focus on developing advanced optimization and learning algorithms for cooperative and competitive multi-agent systems. His research has revealed fundamental but crucial relationships among control, optimization, and learning in complex networked systems. His research not only contributes significantly to theoretical guarantees of desired optimal behaviors, but also catalyzes a number of engineering applications in optimal and sustainable scheduling of power resources and wind farms. He is one of the most active researchers in distributed optimisation and learning. In his research field, he has authored or co-authored more than 20 papers in well-recognised journals and conferences, including IEEE Transactions on Automatic Control, Automatica, IEEE Transactions on Cybernetics, and IEEE Transactions on Neural Networks and Learning Systems, among others. Dr. Li serves as an Associate Editor for Drones and Autonomous Vehicles, and a Guest Editor for Frontiers in Control Engineering. He is an active reviewer for top journals such as IEEE Transactions on Neural Networks and Learning Systems, Automatica, and IEEE Transactions on Cybernetics

Affiliations and expertise

Department of Computer Science, University College London, UK

Zhengtao Ding

Zhengtao Ding is a professor of control systems in the Department of Electrical and Electronic Engineering, at the University of Manchester, in the United Kingdom. He has authored and co-authored three books, including the book Nonlinear and Adaptive Control Systems (IET, 2013), and the book Cooperative Control of Multi-Agent Systems: An Optimal and Robust Perspective (Academic Press, Elsevier, 2020). Dr. Ding has published over 300 research articles, with most of them in leading academic journals in his research area. His research interests include nonlinear and adaptive control theory and their applications, more recently network-based control, distributed optimization, and distributed machine learning, with applications to power systems and robotics. He serves as the Editor-in-Chief for Drones and Autonomous Vehicles, and the Specialty Chief Editor for Nonlinear Control for Frontiers in Control Engineering. He also serves as the Editor-in-Chief for an encyclopedia in the systems and control subject area, commissioned by Elsevier. He is an associate editor and past associate editor for a number of journals, including Scientific Reports, International Journal of Systems Sciences, Journal of Franklin Institute, IEEE Transactions on Automatic Control, among others. He is a member of the IEEE Technical Committee on Nonlinear Systems and Control, IEEE Technical Committee on Intelligent Control, and IFAC Technical Committee on Adaptive and Learning Systems. He is a Fellow of The Alan Turing Institute, the U.K.’s national institute for data science and artificial intelligence.

Affiliations and expertise

Department of Electrical and Electronic Engineering, University of Manchester, UK

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health