讲座题目：Information Based Complexity for High Dimensional Statistical Models
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 ID：683 4896 5096
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).
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．