Auto-Encoding Knockoff Generator for FDR Controlled Variable Selection

Ying Liu, Cheng Zheng

Abstract: A new statistical procedure (Candès,2018) has provided a way to identify important factors using any supervised learning method controlling for FDR. This line of research has shown great potential to expand the horizon of machine learning methods beyond the task of prediction, to serve the broader need for scientific researches for interpretable findings. However, the lack of a practical and flexible method to generate knockoffs remains the major obstacle for wide application of Model-X procedure. This paper fills in the gap by proposing a model-free knockoff generator which approximates the correlation structure between features through latent variable representation. We demonstrate our proposed method can achieve FDR control and better power than two existing methods in various simulated settings and a real data example for finding mutations associated with drug resistance in HIV-1 patients.

Keywords: Model-X Knockoff Generator, model-free FDR control, variable selection

TL;DR: This paper provide model free method for generating Knockoffs, which is critical step in Model-X procedure to choose important variables with any supervised learning method under rigorous FDR control.