Year: 2023
Type: conference-paper
Abstract: 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.
Authors: Zhu, Banghua, Wang, Lun, Pang, Qi, Wang, Shuai, Jiao, Jiantao, Song, Dawn, Jordan, Michael I.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7036427421
