EECI IGSC 2025
Multi-agent optimization and learning: resilient and adaptive solutions
University College London, London, UK
May 6-9, 2025
Register here!
Welcome to the EECI Internationl Graduate School On Control (IGSC) course
"Multi-agent optimization and learning: resilient and adaptive solutions"
by lecturers Dr. Nicola Bastianello (KTH), Prof. Ruggero Carli (University of Padova), and Prof. Luca Schenato (University of Padova).
The course will take place on May 6-9, 2025 at University College London, UK, hosted by Prof. Francesca Boem.
Register here!
Summary: Recent technological advances have enabled the widespread adoption of intelligent devices in many applications. These devices are equipped with communication and computational resources, which allow them to learn from the data they collect. However, in order to improve the accuracy of the models they train, the important paradigm of decentralized learning is being deployed. Therefore, there is a need for algorithmic advances that can support cooperative learning and optimization. The course will provide a thorough introduction to the state of the art in decentralized learning, both with federated and peer-to-peer communication architectures. The course will cover different algorithmic approaches, e.g. gradient-based and dual methods. A particular emphasis will be given to the practical challenges that arise in this context, such as asynchrony and limited communications.
Outline
Introduction and motivating examples (healthcare, smart grids, sensor networks)
Decentralized learning and optimization
From centralized to decentralized
Practical challenges
Decentralized cooperative architectures
Federated learning
Privacy and robustness
Consensus and distributed optimization
The consensus algorithm: standard, accelerated, push-sum/ratio, broadcast w/ faulty communications
Consensus-based distributed optimization: gradient tracking and Newton
Non-expansive operators for optimization: background, operator-based algorithms (proximal gradient, ADMM, primal-dual, …)
Application to decentralized asynchronous and lossy networks: a stochastic operators approach
Current trends
Online distributed optimization (prediction-correction, control-theoretical approaches)
Data-driven optimization, privacy, human-in-the-loop
Hands-on coding experiences