FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participation

2022/03/28 by Han Wang, Wang, Han, Siddartha Marella +3 · 1 citation
Computer Science · #Distributed Sensor Networks and Detection Algorithms #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Mathematics #Machine Learning (cs.LG) #Optimization and Control (math.OC) #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2203.15104

openalex publication_date 2022/03/28 · openalex created_date 2022/04/03 · openalex updated_date 2026/07/28

Abstract

Federated learning is a framework for distributed optimization that places emphasis on communication efficiency. In particular, it follows a client-server broadcast model and is particularly appealing because of its ability to accommodate heterogeneity in client compute and storage resources, non-i.i.d. data assumptions, and data privacy. Our contribution is to offer a new federated learning algorithm, FedADMM, for solving non-convex composite optimization problems with non-smooth regularizers. We prove converges of FedADMM for the case when not all clients are able to participate in a given communication round under a very general sampling model.

Cited by

• An Asynchronous Decentralised Optimisation Algorithm for Nonconvex Problems

Related

• Federated Composite Optimization
• FedCanon: Non-Convex Composite Federated Learning with Efficient Proximal Operation on Heterogeneous Data
• Composite federated learning with heterogeneous data
• Fast Composite Optimization and Statistical Recovery in Federated Learning
• DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime