Byzantine-Robust Federated Learning with Optimal Statistical Rates
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:3151-3178, 2023.
We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates based on recent progress in high dimensional robust statistics. In contrast to prior work, our proposed protocols improve the dimension dependence and achieve a near-optimal statistical rate for strongly convex losses. We also provide statistical lower bound for the problem. For experiments, we benchmark against competing protocols and show the empirical superiority of the proposed protocols.