Federated Asymptotics: a model to compare federated learning algorithms

We propose an asymptotic framework to analyze the performance of (personalized) federated learning algorithms. In this new framework, we formulate federated learning as a multi-criterion objective, where the goal is to minimize each client's loss using information from all of the clients. We an...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Cheng, Gary, Chadha, Karan, Duchi, John
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 18.02.2022
Subjects
Algorithms
Asymptotic properties
Criteria
Machine learning
Regression models
Online AccessGet full text

Cover

More Information
Summary:We propose an asymptotic framework to analyze the performance of (personalized) federated learning algorithms. In this new framework, we formulate federated learning as a multi-criterion objective, where the goal is to minimize each client's loss using information from all of the clients. We analyze a linear regression model where, for a given client, we may theoretically compare the performance of various algorithms in the high-dimensional asymptotic limit. This asymptotic multi-criterion approach naturally models the high-dimensional, many-device nature of federated learning. These tools make fairly precise predictions about the benefits of personalization and information sharing in federated scenarios -- at least in our (stylized) model -- including that Federated Averaging with simple client fine-tuning achieves the same asymptotic risk as the more intricate meta-learning and proximal-regularized approaches and outperforming Federated Averaging without personalization. We evaluate these predictions on federated versions of the EMNIST, CIFAR-100, Shakespeare, and Stack Overflow datasets, where the experiments corroborate the theoretical predictions, suggesting such frameworks may provide a useful guide to practical algorithmic development.
ISSN:2331-8422