学术报告

       全校师生：

       我校定于2021年11月19日举办研究生灵犀学术殿堂——Ryan Martin教授报告会，现将有关事项通知如下：

       1.报告会简介

       报告人：Ryan Martin教授

       时间：2021年11月19日（星期五）下午20:00（开始时间）

       地点：腾讯会议163 855 973

       报告题目：Generalized inferential models: Basics and beyond

       内容简介：Statistics aims to quantify uncertainty about unknowns based on data. To formalize this, an inferential model (IM) is a function that maps data, etc., to a probability-like structure that assigns data-dependent degrees of belief to assertions about the unknowns. In order for the IM to be reliable, or *valid*, it's necessary that its output take the form of an imprecise probability. Constructions of valid IMs are available, but the first strategies could only be carried out in simple textbook-style problems. The generalized IM approach simplifies the construction and creates opportunities for new solutions to important modern inference and prediction problems. In this talk, I'll present the basic IM framework, the generalized IM construction, and several applications. In particular, I'll talk about inference in censored-data problems, nonparametric or model-free prediction, and inference on risk minimizers as is often of interest in machine learning applications.

党委学生工作部

数学与统计学院

2021年11月15日

       报告人简介

       Ryan Martin，美国北卡罗莱纳州立大学统计系教授。2009年博士毕业于普渡大学统计系。研究方向为不确定推理、广义贝叶斯推理、不精确概率论、机器学习等。他的研究工作得到了美国国家科学基金会、美国陆军、国家安全局和精算师协会等资助。目前在Annals of Statistics、Journal of the American Statistical Association、Journal of the Royal Statistical Society：Series B、Biometrika等统计学顶级期刊上发表数十篇专业学术论文，出版专著《Inferential Models：Reasoning with Uncertainty》。