The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
Optimal Online Control Strategy for Differentially Private Federated Learning
- Published
- Record updated
Summary
This paper proposes an optimal control framework for (ε, δ)-differentially private federated learning that jointly and adaptively sets the DP noise variance and the number of communication rounds, based on training accuracy. The authors derive the optimality gap under this framework. In experiments on MLP, CNN and ResNet-9 models, the framework lets DP-FL converge faster and reach better accuracy than existing techniques at a given privacy level.