Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses

Changyu Gao; Andrew Lowy; Xingyu Zhou; Stephen Wright

2024 ICML ICML 2024

Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

Authors

Changyu Gao, Andrew Lowy, Xingyu Zhou, Stephen Wright

Topics

Machine Learning > Optimization & Theory > Optimization Machine Learning > Application Areas > Efficient Computing Mathematics & Optimization > Optimization > Convex Optimization

Keywords

differential privacy communication complexity excess risk heterogeneous data smooth function convex losses

Download PDF