9月23日 袁明:Information Based Complexity for High Dimensional Statistical Models(69周年校庆系列学术报告)

来源:pt真人平台 时间:2020-09-15浏览:19设置


讲座题目:Information Based Complexity for High Dimensional Statistical Models

主讲人:袁明  教授

主持人:周勇  教授

开始来源:pt真人平台 时间:2020-09-23 09:00:00   结束来源:pt真人平台 时间:2020-09-23   10:00:00

讲座地址:线上 Zoom会议  ID683 4896 5096

主办单位:经济与管理学部

 

报告人简介:

Ming Yuan is Professor  of Statistics at Columbia University. He was previously Senior Investigator   in Virology at Morgridge Institute for Research and Professor of Statistics   at University of Wisconsin at Madison, and prior to that Coca-Cola Junior   Professor of Industrial and Systems Engineering at Georgia Institute of   Technology. His research and teaching interests lie broadly in statistics and   its interface with other quantitative and computational fields such as   optimization, machine learning, computational biology and financial  engineering. He has over 100 scientific publications in applied mathematics,  computer science, electrical engineering, financial econometrics, medical   informations, optimization, and statistics among others. He is currently   serving as the program secretary of the Institute for Mathematical Statistics   (IMS), and a member of the advisory board for the Quality, Statistics and   Reliability (QSR) section of the Institute for Operations Research and the   Management Sciences (INFORMS). He is also a co-Editor of The Annals of   Statistics and has been serving on numerous editorial boards. He was named a   Medallion Lecturer of IMS in 2018, and a recipient of the John van Ryzin   Award (2004; International Biometrics Society), CAREER Award (2009; US   National Science Foundation), the Guy Medal in Bronze (2014; Royal   Statistical Society), and the Leo Breiman Junior Researcher Award (2017; the   Statistical Learning and Data Mining section of the American Statistical   Association).

 

报告内容:

I will introduce a coherent framework to   quantify the complexity of high dimensional models that appropriately accounts for both statistical accuracy and computational cost and better  understand the potential trade-off between the two types of efficiencies and. As an example, I will use this notion of complexity to examine   high-dimensional and sparse nonparametric problems to illustrate how this can   lead to the development of novel and optimal sampling and estimation strategies, and in particular reveal the role of experimental design in  alleviating computational burden

 


返回原图
/