From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning. (arXiv:2302.12559v1 [cs.LG])

We study differentially private (DP) machine learning algorithms as instances
of noisy fixed-point iterations, in order to derive privacy and utility results
from this well-studied framework. We show that this new perspective recovers
popular private gradient-based methods like DP-SGD and provides a principled
way to design and analyze new private optimization algorithms in a flexible
manner. Focusing on the widely-used Alternating Directions Method of
Multipliers (ADMM) method, we use our general framework to derive novel private
ADMM algorithms for centralized, …

algorithms design federated learning framework machine machine learning machine learning algorithms optimization order perspective point popular privacy private results study utility