Oct 21 2020

Statistics and Data Science Seminar: Model-free Feature Screening and FDR Control with Knockoff Features, by Yuan Ke

October 21, 2020

4:00 PM - 4:50 PM




Chicago, IL

Yuan Ke (University of Georgia): Model-free Feature Screening and FDR Control with Knockoff Features

We proposes a model-free and data-adaptive feature screening method for ultra-high dimensional data. The proposed method is based on the projection correlation which measures the dependence between two random vectors. This projection correlation based method does not require specifying a regression model, and applies to data in the presence of heavy tails and multivariate responses. It enjoys both sure screening and rank consistency properties under weak assumptions. A two-step approach, with the help of knockoff features, is advocated to specify the threshold for feature screening such that the false discovery rate (FDR) is controlled under a pre-specified level. The proposed two-step approach enjoys both sure screening and FDR control simultaneously if the pre-specified FDR level is greater or equal to 1/s, where s is the number of active features. The superior empirical performance of the proposed method is illustrated by simulation examples and real data applications.

Please click here to make changes to, or delete, this seminar announcement.


Yichao Wu

Date posted

Oct 21, 2020

Date updated

Oct 21, 2020


Yuan Ke | (University of Georgia)