Skip to yearly menu bar Skip to main content

Workshop: OPT 2022: Optimization for Machine Learning

A Unified Framework to Understand Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective

xinwei zhang · Nicola Elia · Mingyi Hong


Distributed algorithms have been playing an increasingly important role in many applications such as machine learning, signal processing, and control. In this work, we provide a fresh perspective to understand, analyze, and design distributed optimization algorithms. Through the lens of multi-rate feedback control, we show that a wide class of distributed algorithms, including popular decentralized/federated schemes, can be viewed as discretizing a certain continuous-time feedback control system, possibly with multiple sampling rates, such as decentralized gradient descent, gradient tracking, and federated averaging. This key observation not only allows us to develop a generic framework to analyze the convergence of the entire algorithm class. More importantly, it also leads to an interesting way of designing new distributed algorithms. We develop the theory behind our framework and provide examples to highlight how the framework can be used in practice.

Chat is not available.