报告题目：Inherent Privacy for Distributed Optimization and Learning
报告人：王永强，Clemson University
报告时间：2022年7月25日9:00-10:00
内容简介：
Distributed (stochastic) optimization is the basic building block of modern collaborative machine learning, distributed estimation and control, and large-scale sensing. Since involved data usually contain sensitive information like users’locations, healthcare records, or financial transactions, privacy protection has become an increasingly pressing need in the implementation of distributed optimization and learning algorithms. However, existing privacy solutions usually incur heavy communication/computation overhead or sacrifice optimization/learning accuracy. We propose to judiciously embed stochasticity on the algorithmic level to enable privacy without incurring heavy communication/computation overhead or accuracy loss. Besides rigorous theoretical analysis, simulation results as well as numerical experiments on a benchmark machine learning dataset confirm the effectiveness of the proposed approach.
报告人简介：
Yongqiang Wang received the dual B.S. degrees in electrical engineering & automation and computer science & technology from Xi'an Jiaotong University, Xi'an, Shaanxi, China, in 2004, and the Ph.D. degree in control science and engineering from Tsinghua University, Beijing, China, in 2009. From 2007-2008, he was with the University of Duisburg-Essen, Germany, as a visiting student. He was a project scientist at the University of California, Santa Barbara before joining Clemson University, SC, USA, where he is currently an Associate Professor. His current research interests include distributed control, optimization, and learning, with an emphasis on privacy protection. He currently serves as an associate editor for IEEE Transactions on Automatic Control, IEEE Transactions on Control of Network Systems, and IEEE Transactions on Signal and Information Processing over Networks.
