Adaptive Federated Optimization
From MaRDI portal
Publication:6335874
arXiv2003.00295MaRDI QIDQ6335874
Author name not available (Why is that?)
Publication date: 29 February 2020
Abstract: Federated learning is a distributed machine learning paradigm in which a large number of clients coordinate with a central server to learn a model without sharing their own training data. Standard federated optimization methods such as Federated Averaging (FedAvg) are often difficult to tune and exhibit unfavorable convergence behavior. In non-federated settings, adaptive optimization methods have had notable success in combating such issues. In this work, we propose federated versions of adaptive optimizers, including Adagrad, Adam, and Yogi, and analyze their convergence in the presence of heterogeneous data for general non-convex settings. Our results highlight the interplay between client heterogeneity and communication efficiency. We also perform extensive experiments on these methods and show that the use of adaptive optimizers can significantly improve the performance of federated learning.
Has companion code repository: https://github.com/KarhouTam/FL-bench
This page was built for publication: Adaptive Federated Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6335874)
