Adaptive federated optimization

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. Due to the heterogeneity of the client datasets, 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 nonconvex 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.

optimization and control

Audience: researchers in the topic

Federated Learning One World Seminar

Series comments: Description: Research seminar on federated learning and related fields

Please register for the seminar on the website here (https://sites.google.com/view/one-world-seminar-series-flow/register#h.eoftjj4xztpb). Prior to the beginning of the seminar, a Zoom link with a password will be sent to the e-mail addresses of the people who have registered to be included in the mailing list.