报告题目【Sufficient Dimension Reduction for Classification】
时间: 2019年5月5日（星期日）10：30
地点: 旗山校区理工北楼601报告厅
主讲: 南方科技大学副教授，陈欣
主办: 数学与信息学院
参加对象：感兴趣的老师和学生
报告人简介：Dr Chen got his bachelor degree from Nankai University and his PHD from University of Minnesota. He currently works in Southern University of Science and Technology. His research area includes dimension reduction, variable selection and high dimensional analysis.
摘要: In this talk, we talk about a new sufficient dimension reduction approach designed deliberately for high-dimensional classification. This novel method is named maximal mean variance (MMV), inspired by the mean variance index first proposed by Cui, Li and Zhong (2015), which measures the dependence between a categorical random variable with multiple classes and a continuous random variable. Our method requires reasonably mild restrictions on the predicting variables and keeps the model-free advantage without the need to estimate the link function. Our method works pretty well when n < p. The surprising classification efficiency gain of the proposed method is demonstrated by simulation studies and real data analysis.