Solution Paths for Large p Small n Problems

摘要：In this talk, we will introduce a new but very simple framework to solve the large p small n problems. The framework decomposes the data into pieces so that existing methods can be applied. We propose two separate paths to implement the framework. Our paths provide sufficient procedures for identifying informative variables sequentially.  The paths are very general and we shall illustrate their efficacy via simulation and a real data set by using sufficient dimension reduction and variable selection methods.

Xiangrong Yin（殷向荣）为美国 Georgia 大学统计系教授，美国统计学会图像统计方向八个创始人之一。现担任国际统计界学术期刊 Journal of Nonparametric Statistics、Statistics and Probability Letters副主编。先后被选为美国统计学会（American Statistical Association）、国际数理统计学会（Institute of

Mathematical Statistics，IMS）、国际泛华统计学会（International Chinese Statistical Association，ICSA）终身会员。