Auto-Encoding Knockoff Generator for FDR Controlled Variable Selection

Abstract

A new statistical procedure (Model-X \cite{candes2018}) 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 needs in 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.

arXiv commentIn submission

References in corpus (3)

• Auto-Encoding Variational Bayes
• Categorical Reparameterization with Gumbel-Softmax
• Knockoffs for the mass: new feature importance statistics with false discovery guarantees

Cited by in corpus (8)

• Deep Knockoffs
• Metropolized Knockoff Sampling
• Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importance
• Conditional Feature Importance for Mixed Data
• Knockoffs with Side Information
• Discovering Conditionally Salient Features with Statistical Guarantees
• Semi-supervised multiple testing
• Deep Direct Likelihood Knockoffs