报告人：黄廷文教授

工作单位：德州农工大学卡塔尔分校（卡塔尔）

报告题目：基于随机梯度的分布式优化理论与应用

报告时间：2023年4月13日（周四）14:30-15:30

报告链接：Teams Link

https://teams.microsoft.com/l/meetup-join/19%3aB4gmRcUATAMA2iJqi-xXvtfPFfTbxVJPxSW_pcAPBao1%40thread.tacv2/1638719716825?context=%7b%22Tid%22%3a%2222804ebb-30d5-47df-942f-f3a3722f0225%22%2c%22Oid%22%3a%2216a60c03-ad7a-4b85-a403-8ebd947e010c%22%7d 

内容摘要：

   首先，该报告将介绍分布式优化的研究背景，包括一些优化模型在智能电网、交通网络的应用，以及使用分布式优化的理由。其次，将对分布式优化的研究现状进行概述，包括对处理底层有向或无向图各种算法的简要介绍，这些算法有不同的收敛率。最后，将介绍我们最近在基于随机梯度的分布式优化方面的工作，包括：每个节点的期望值能够收敛到最优解，步长范围可以确定，并且能够达到线性收敛率。

个人简介：  

   黄廷文教授于1990年在中国西南大学获得学士学位，1993年在中国四川大学获得硕士学位，2002年在德克萨斯A&M大学获得博士学位。从德克萨斯A&M大学毕业后，他在那里担任客座助理教授。之后，他于2003年8月加入位于卡塔尔的德克萨斯A&M大学，担任助理教授，后于2013年晋升为教授。黄廷文教授的研究领域包括神经网络、混沌动力系统、复杂网络、优化和控制、智能电网等。黄廷文教授在2015年获卡塔尔国家研究基金最佳研究项目，在2022年获亚太神经网络协会杰出成就奖，在2022年获德克萨斯A&M大学教师最高荣誉--前任学生协会杰出研究成就奖。目前，黄廷文教授是IEEE及IAPR的会员。

                                             【编辑：王健】

英文版：

Academic Report Notice of Tingwen Huang：Theory and Applications of Distributed Optimization Based on Stochastic Gradient

Speaker: Professor  Tingwen Huang

Title: Theory and Applications of Distributed Optimization Based on Stochastic Gradient

Time: 14:30-15:30, April 13th, 2023 (Thursday)

Website: Teams Link

https://teams.microsoft.com/l/meetup-join/19%3aB4gmRcUATAMA2iJqi-xXvtfPFfTbxVJPxSW_pcAPBao1%40thread.tacv2/1638719716825?context=%7b%22Tid%22%3a%2222804ebb-30d5-47df-942f-f3a3722f0225%22%2c%22Oid%22%3a%2216a60c03-ad7a-4b85-a403-8ebd947e010c%22%7d 

Abstract: 

  First, the research background on distributed optimization is presented. This includes introductions on some optimization models and applications to smart grid, transportation networks, the reasons for using distributed optimization. Then, overview of the current study status on distributed optimization is presented. This contains the brief introduction on various algorithms in dealing the underlying directed or undirected graphs with different convergent rates. Finally, our recent work on distributed optimization based on the stochastic gradient are presented. The new results include: the expectation of each node can converge to the optimal solution, the range for step sizes can be determined, linear convergent rate can be reached.

Personal Introduction: 

  Tingwen Huang is a Professor at Texas A&M University at Qatar. He received his B.S. degree from Southwest University, China, 1990, his M.S. degree from Sichuan University, China, 1993, and his Ph.D. degree from Texas A&M University, College Station, Texas, 2002. After graduated from Texas A&M University, he worked as a Visiting Assistant Professor there. Then he joined Texas A&M University at Qatar as an Assistant Professor in August 2003, then he was promoted to Professor in 2013. Dr. Huang’s research areas include neural networks, chaotic dynamical systems, complex networks, optimization and control, smart grid. He was conferred Best Research Project Award by Qatar National Research Fund in 2015, Outstanding Achievement Award by Asia Pacific Neural Networks Society in 2022, The Association of Former Students Distinguished Achievement Award for Research, the highest honor bestowed to a faculty by Texas A&M University in 2022. He a Fellow of IEEE and IAPR.

                                                                                                                                          [Editor:Jian Wang]