数学与统计学院学术报告[2021] 136号

(高水平大学建设系列报告636号)

报告题目: Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference

报告人：刘卫东 教授（上海交通大学）

报告时间：12月04日10:00-11:00

报告地点：腾讯会议：202-695-761  

报告内容：

This paper develops an efficient distributed inference algorithm,  which is robust against a moderate fraction of Byzantine nodes, namely arbitrary and possibly adversarial machines in a distributed learning system. In robust statistics, the median-of-means (MOM) has been a popular approach to hedge against Byzantine failures due to its ease of implementation and computational efficiency. However, the MOM estimator has the shortcoming in terms of statistical efficiency. The first main contribution of the paper is to propose a variance reduced median-of-means (VRMOM) estimator, which improves the statistical efficiency over the vanilla MOM estimator and is computationally as efficient as the MOM. Based on the proposed VRMOM estimator, we develop a general distributed inference algorithm that is robust against Byzantine failures.  Theoretically, our distributed algorithm achieves a fast convergence rate with only a constant number of rounds of communications. We also provide the asymptotic normality result for the purpose of statistical inference. To the best of our knowledge, this is the first normality result in the setting of Byzantine-robust distributed learning.　　　The simulation results are also presented to illustrate the effectiveness of our method.

报告人简历：

刘卫东，国家杰出青年科学基金获得者，上海交通大学特聘教授，主要从事现代统计与机器学习的研究，在大数据的分布式算法、高维数据的统计分析等方向做出了系列成果。

欢迎感兴趣的师生参加！

　　　　　　 　　　　　　　　　　　　　　　数学与统计学院

             　　　　　　　　　　　　　2021年12月2日