时 间： 2020年7月11日上午 8:30-11:30
报告人： 谢敏革 教授
主持人： 汤银才 教授
摘 要：
In this short course, we will (1) introduce the concept of confidence distribution and the concept of conformal prediction; (2)describe their roles in statistical foundation in linking existing inference and prediction approaches across frequentist, Bayesian and fiducial paradigms; (3) show how they can be applied broadly to solve a wide range of problems in data science. Specifically, we will discuss several new and effective fusion learning and meta-analysis approaches to combine information from heterogeneous diverse sources. We will also discuss predictive inference problems in data science and provide one explanation why the deep learning and many other black-box machine learning approaches work so well in academic exercises (with experiments set up by randomly splitting the entire data into training and testing data sets), but fail to deliver many“killer applications in real world applications.
个人简介：
Dr. Min-ge Xie (谢敏革) is a Distinguished Professor from Department of Statistics, Rutgers University. He is a noted expert in statistical inference and fusion learning. His pioneer research inconfidence distributions was described as a “grounding process with energy and insight. His other expertise includes conformal prediction,estimating equations, big data, robust statistics, hierarchical models, asymptotics, etc. Dr. Xie received his BS degree in mathematics from University of Science and Technology (USTC) with high honor and PhD degree in statistics from University of Illinois at Urbana-Champaign (UIUC). He has published 80+research articles and served in a number of journal editorial boards including JASA, Statistical Science, Science China-Mathematics and others. His research has been supported in part by research grants from the US National Science Foundation (NSF), the US National Institute of Health (NIH) and the US Department of Homeland Security.