@inproceedings{bietti2022personalization,
author = {Bietti, Alberto and Wei, Chen-Yu and Dudík, Miro and Langford, John and Wu, Steven},
title = {Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization},
booktitle = {ICML 2022},
year = {2022},
month = {July},
abstract = {Large-scale machine learning systems often involve data distributed across a collection of users. Federated optimization 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 show 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.},
url = {http://approjects.co.za/?big=en-us/research/publication/personalization-improves-privacy-accuracy-tradeoffs-in-federated-optimization/},
}