主题：复杂系统与智能科学

报告题目：Distributed multi-agent optimization via mirror descent

报告人：袁德明

报告时间：2023.6.16（星期五）15：30，腾讯会议：739 574 168

内容简介：

In this talk we consider convergence rate problems for stochastic strongly-convex optimization in the non-Euclidean sense with a constraint set over a time-varying multi-agent network. We propose two efficient non-Euclidean stochastic subgradient descent algorithms based on the Bregman divergence as distance-measuring function rather than the Euclidean distances that were employed by the standard distributed stochastic projected subgradient algorithms. For distributed optimization of non-smooth and strongly convex functions whose only stochastic subgradients are available, the first algorithm recovers the best previous known rate of O(ln(T)/T) (where T is the total number of iterations). The second algorithm is an epoch variant of the first algorithm that attains the optimal convergence rate of O(1/T), matching that of the best previously known centralized stochastic subgradient algorithm.

报告人简介：

袁德明，于2007年7月、2012年6月毕业于南京理工大学，分别获工学学士和工学博士学位；现为南京理工大学自动化学院教授，博士生导师，澳大利亚“奋进”研究学者。主要从事分布式优化、学习与控制相关研究。近年来，在IEEE Transactions on Information Theory、IEEE Transactions on Automatic Control、Automatica、SIAM Journal on Control and Optimization等学术刊物发表论文数篇。2020年获国家自然科学基金优秀青年基金资助，2017年获江苏省自然科学基金优秀青年基金资助，同时主持并参与多项国家和江苏省自然科学基金。目前担任国际刊物Journal of the Franklin Institute、Transactions of the Institute of Measurement and Control、Franklin Open编委。