RANK: Large-Scale Inference with Graphical Nonlinear Knockoffs
arXiv:1709.00092
Abstract
Power and reproducibility are key to enabling refined scientific discoveries in contemporary big data applications with general high-dimensional nonlinear models. In this paper, we provide theoretical foundations on the power and robustness for the model-free knockoffs procedure introduced recently in Candès, Fan, Janson and Lv (2016) in high-dimensional setting when the covariate distribution is characterized by Gaussian graphical model. We establish that under mild regularity conditions, the power of the oracle knockoffs procedure with known covariate distribution in high-dimensional linear models is asymptotically one as sample size goes to infinity. When moving away from the ideal case, we suggest the modified model-free knockoffs method called graphical nonlinear knockoffs (RANK) to accommodate the unknown covariate distribution. We provide theoretical justifications on the robustness of our modified procedure by showing that the false discovery rate (FDR) is asymptotically controlled at the target level and the power is asymptotically one with the estimated covariate distribution. To the best of our knowledge, this is the first formal theoretical result on the power for the knockoffs procedure. Simulation results demonstrate that compared to existing approaches, our method performs competitively in both FDR control and power. A real data set is analyzed to further assess the performance of the suggested knockoffs procedure.
37 pages, 6 tables, 9 pages supplementary material
References in corpus (9)
- High-dimensional classification using features annealed independence rules
- Size, power and false discovery rates
- Robustness of multiple testing procedures against dependence
- On false discovery control under dependence
- Generalized Additive Model Selection
- Innovated interaction screening for high-dimensional nonlinear classification
- A Selective Overview of Variable Selection in High Dimensional Feature Space (Invited Review Article)
- Ultrahigh dimensional variable selection: beyond the linear model
- Nonuniformity of P-values Can Occur Early in Diverging Dimensions