受我院刘应状教授的邀请，麻省理工学院Lizhong Zheng（郑立中）教授将于本月中旬访问我校。郑教授是无线通信与信息论领域的领军人物，其博士期间的两篇突破性论文——非相干MIMO信道的容量刻画以及分集-复用增益折衷的理论框架——即已奠定令人瞩目的学术地位；其工作以关注学科根本性问题，研究结果深刻、简洁且优雅著称。
1月12日上午9:30，在武汉光电国家实验室A101室，郑教授将进行一场关于将信息论应用于统计推断的学术报告。除了技术部分，报告还将重点涉及研究方法论的讨论，特别地，将涉及如何从EE的视角进行Big Data（大数据）相关问题的研究，以及EE与CS在研究Big Data问题上的风格差异。
本报告无须信息论的相关背景，欢迎感兴趣的师生（包括本科生）参加。
Statistical Inference via Information Geometry
--An Example of “EE Style” Research in the Big Data Era
Speaker: Prof.Lizhong Zheng, MIT
Time：9：30 AM, Jan. 12, 2015
Location: Rm. A101,Wuhan National Lab. for Optoelecronics.
Abstract:
This talkhas a technical part and a non-technical part.
Thetechnical part is an overview of our new results on applying informationgeometry on statistical inference problems. We explain some limitations of theconventional information theoretic analysis, and present a method to go beyondsuch limits. This involves a new formulation of the inference problems, a newset of information metrics, and new operational meanings of these metrics inthe context of data processing. We argue that our approach is a fundamentalextension of the conventional approaches, and a key to put a systematicframework to the new machine learning type of problems.
I thenon-technical part of this talk, we try to report some new trends in thedevelopment of the theory for information technology, and the differencebetween an EE-style and a CS-style research. This reflects our personal tastesin picking research problems and in driving the direction of fundamentalresearch, with the hope of motivating more students in pursuing researchresults from a diverse range of directions.
Bio:
Lizhong Zheng received the B.S and M.S. degrees, in 1994and 1997 respectively, from the Department of Electronic Engineering, TsinghuaUniversity, China, , and the Ph.D. degree, in 2002, from the Department ofElectrical Engineering and Computer Sciences, University of California,Berkeley. Since 2002, he has been working in the Department of ElectricalEngineering and Computer Sciences, where he is currently a professor ofElectrical Engineering and Computer Sciences. His research interests includeinformation theory, wireless communications, and statistical inference. Hereceived the IEEE Information Theory Society Paper Award in 2003, and NSFCAREER award in 2004, and the AFOSR Young Investigator Award in 2007.
