首页 - 通知公告 - 正文


【2021/10/27】Innovation Compression for Communication-efficient Distributed Optimization with Linear Convergence

创建时间:  2021/10/26  吴影清   浏览次数:   返回

报告题目

Innovation Compression for Communication-efficient Distributed Optimization with Linear Convergence

个人简介


游科友,清华大学自动化系长聘副教授、博士生导师。2007年获中山大学统计科学学士学位。2007年8月至2012年6月在新加坡南洋理工大学电气与电子工程学院攻读博士学位和从事博士后研究。自2012年7月起任教于清华大学自动化系。曾受邀访问意大利都灵理工大学、澳大利亚墨尔本大学、香港科技大学等院校。长期从事复杂网络化系统的学习、优化与控制及其应用的研究。目前,担任Transactions on Control of Network Systems、IEEE Transactions on Cybernetics、Systems&ControlLetters、IEEEControlSystemLetters等国际期刊副编委(Associate Editor)。先后主持国家自然科学基金委优青项目、重点项目、重点研发计划课题等,获关肇直最佳论文奖、亚洲控制学会淡马锡青年教育学者奖。

报告摘要

Information compression is essential to reduce communication cost in distributed optimization over peer-to-peer networks.Wepropose acommunication-efficientlinearly convergentdistributed (COLD) algorithm to solve strongly convex optimization problems. By compressing innovation vectors, which are the differences between decision vectors and their estimates, COLD is able to achieve linear convergence for a class ofδ-contracted compressors. We explicitly quantify how the compression affects the convergence rate and show that COLD matches the same rate of its uncompressed version. To accommodate a wider class of compressors that includes the binary quantizer, we further design a novel dynamical scaling mechanism and obtain the linearly convergent Dyna- COLD. Importantly, our results strictly improve existing results for the quantized consensus problem. Numerical experiments demonstrate the advantages of both algorithms under different compressors.


报告时间:2021/10/27 16:00-20:00 (GMT+08:00) 中国标准时间 - 北京

点击链接入会,或添加至会议列表:

https://meeting.tencent.com/dm/K1GEbBevAB9Z

会议ID:544 714 676


上一条:【2021/10/27】Recent developments on stability analysis of time-delay systems

下一条:【2021/10/26】模仿人类行为的机器人设计|医疗保健中的人工智能