报告题目：Communication-efficient Byzantine-robust distributed learning with statistical guarantee
报 告 人：周兴才 教授 南京审计大学
报告时间：2021年11月12日 15:00-16:00
报告地点：腾讯会议 ID：244 506 890 会议密码：1112
校内联系人：朱复康 fzhu@jlu.edu.cn
报告摘要：Communication efficiency and robustness are two major issues in modern distributed learning framework. This is due to the practical situations where some computing nodes may have limited communication power or may behave adversarial behaviors. To address the two issues simultaneously, this paper develops two communication-efficient and robust distributed learning algorithms for convex problems. Our motivation is based on surrogate likelihood framework and the median and trimmed mean operations. Particularly, the proposed algorithms are provably robust against Byzantine failures, and also achieve optimal statistical rates for strong convex losses and convex (non-smooth) penalties. For typical statistical models such as generalized linear models, our results show that statistical errors dominate optimization errors in finite iterations. In addition, but also enjoy linear convergence under general conditions. Simulated and real data experiments are conducted to demonstrate the numerical performance of our algorithms.
报告人简介：周兴才，博士，南京审计大学教授、硕士生导师。研究领域为统计机器学习、函数型数据分析。东南大学理学（统计学方向）博士、东南大学应用经济学博士后，加拿大University of Alberta数学与统计系博士后，主持国家自然科学基金面上项目1项、国家社会科学基金（一般项目）1项、教育部人文社科基金1项、省自然科学基金（面上项目）2项、中国博士后基金（特别资助）1项、中国博士后基金（一等资助）2项，参与国家自然科学基金3项、省部级项目3项；累计主持与参加国家、省部级各类项目20余项；在国际统计学期刊发表SCI论文30余篇，其中Journal of the Royal Statistical Society Series B顶级论文1篇。中国现场统计研究会旅游大数据分会常务理事，江苏省应用统计学会理事。
