Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization. (arXiv:2202.05318v1 [stat.ML])

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 …

accuracy arxiv ml optimization personalization privacy