Comment on “Federated Learning With Differential Privacy: Algorithms and Performance Analysis”

A recent research paper by Wei et al. proposes a differential privacy algorithm in the context of Federated Learning and provides its performance analysis, mainly focusing on proving a convergence bound for the loss function. In this paper, we show that some of the mathematical derivations given in Wei et al. are not valid. Thus the bounds they prove in the paper do not hold for all loss functions. In this work, we give the correct derivation of the best possible local sensitivity bound, which is valid for all loss functions. We also state the modifications in the bounds for global sensitivity and the standard deviation of the Gaussian noise added, both before and after aggregation.