A0624
Title: Model-X conditional knockoffs and conditional randomization tests using Gaussian graphical models
Authors: Dongming Huang - National University of Singapore (China) [presenting]
Lucas Janson - Harvard University (United States)
Abstract: The model-X framework provides provable non-asymptotical error control on variable selection and conditional independence testing. It has no restrictions or assumptions on the dimensionality of the data or the conditional distribution of the response given the covariates. To relax the requirement of the model-X framework that the distribution of the covariate samples is precisely known, it is proposed to construct knockoffs by conditioning on sufficient statistics when the distribution is known up to a parametric model with as many as Cnp parameters, where p is the dimension, n is the number of covariate samples (including unlabeled samples if available), and C is a constant. It is demonstrated how this idea can be implemented in Gaussian graphical models, and the new approach remains powerful under the weaker assumption. It is shown how such conditioning can be extended to constructing a conditional randomization test for testing conditional independence between the response and a subset of the covariates.
