2022-06-28-bietti22a.md

title	booktitle	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning	Proceedings of the 39th International Conference on Machine Learning	Large-scale machine learning systems often involve data distributed across a collection of users. Federated learning algorithms leverage this structure by communicating model updates to a central server, rather than entire datasets. In this paper, we study stochastic optimization algorithms for a personalized federated learning setting involving local and global models subject to user-level (joint) differential privacy. While learning a private global model induces a cost of privacy, local learning is perfectly private. We provide generalization guarantees showing that coordinating local learning with private centralized learning yields a generically useful and improved tradeoff between accuracy and privacy. We illustrate our theoretical results with experiments on synthetic and real-world datasets.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	bietti22a	0	Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning	1945	1962	1945-1962	1945	false	Bietti, Alberto and Wei, Chen-Yu and Dudik, Miroslav and Langford, John and Wu, Steven	given family Alberto Bietti given family Chen-Yu Wei given family Miroslav Dudik given family John Langford given family Steven Wu	2022-06-28		Proceedings of the 39th International Conference on Machine Learning	162	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v162/bietti22a/bietti22a.pdf