paper-with-me

홈 › Papers

Understanding A Class of Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective

2022-04-27 · Xinwei Zhang, Mingyi Hong, Nicola Elia

Distributed algorithms have been playing an increasingly important role in many applications such as machine learning, signal processing, and control. Significant research efforts have been devoted to developing and analyzing new algorithms for various applications. 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.

📄 PDF Abstract BibTeX arXiv:2204.12663

Code (0)

등록된 구현이 없습니다.

Tasks

Distributed Optimization

Similar Papers 제목 키워드 기반

When Decentralized Optimization Meets Federated Learning

2023-06-05 · Hongchang Gao, My T. Thai, Jie Wu

Federated learning is a new learning paradigm for extracting knowledge from distributed data. Due to its favorable properties in preserving privacy and saving communication costs, it has been extensively studied and wide…

Federated Learning

Second-Order Guarantees in Federated Learning

2020-12-02 · Stefan Vlaski, Elsa Rizk, Ali H. Sayed

Federated learning is a useful framework for centralized learning from distributed data under practical considerations of heterogeneity, asynchrony, and privacy. Federated architectures are frequently deployed in deep le…

Deep LearningFederated Learning

One Gradient Frank-Wolfe for Decentralized Online Convex and Submodular Optimization

2022-10-30 · Tuan-Anh Nguyen, Nguyen Kim Thang, Denis Trystram

Decentralized learning has been studied intensively in recent years motivated by its wide applications in the context of federated learning. The majority of previous research focuses on the offline setting in which the o…

Federated Learning

SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication

2022-10-25 · Marco Bornstein, Tahseen Rabbani, Evan Wang, Amrit Singh Bedi 외

The decentralized Federated Learning (FL) setting avoids the role of a potentially unreliable or untrustworthy central host by utilizing groups of clients to collaboratively train a model via localized training and model…

Federated Learningimage-classificationImage Classification

A survey on secure decentralized optimization and learning

2024-08-16 · Changxin Liu, Nicola Bastianello, Wei Huo, Yang Shi 외

Decentralized optimization has become a standard paradigm for solving large-scale decision-making problems and training large machine learning models without centralizing data. However, this paradigm introduces new priva…

Decision MakingDistributed OptimizationPrivacy PreservingSurvey