Metropolized Knockoff Sampling
From MaRDI portal
Abstract: Model-X knockoffs is a wrapper that transforms essentially any feature importance measure into a variable selection algorithm, which discovers true effects while rigorously controlling the expected fraction of false positives. A frequently discussed challenge to apply this method is to construct knockoff variables, which are synthetic variables obeying a crucial exchangeability property with the explanatory variables under study. This paper introduces techniques for knockoff generation in great generality: we provide a sequential characterization of all possible knockoff distributions, which leads to a Metropolis-Hastingsformulation of an exact knockoff sampler. We further show how to use conditional independence structure to speed up computations. Combining these two threads, we introduce an explicit set of sequential algorithms and empirically demonstrate their effectiveness. Our theoretical analysis proves that our algorithms achieve near-optimal computational complexity in certain cases. The techniques we develop are sufficiently rich to enable knockoff sampling in challenging models including cases where the covariates are continuous and heavy-tailed, and follow a graphical model such as the Ising model.
Recommendations
Cites work
- A Separator Theorem for Planar Graphs
- Beitrag zur Theorie des Ferromagnetismus
- Complexity of Finding Embeddings in a k-Tree
- Controlling the false discovery rate via knockoffs
- Deep knockoffs
- Equation of state calculations by fast computing machines
- Gene hunting with hidden Markov model knockoffs
- scientific article; zbMATH DE number 1964693 (Why is no real title available?)
- IPAD: stable interpretable forecasting with knockoffs inference
- Monte Carlo sampling methods using Markov chains and their applications
- Multipoint Metropolis method with application to hybrid Monte Carlo
- Nonserial dynamic programming
- Panning for Gold: ‘Model-X’ Knockoffs for High Dimensional Controlled Variable Selection
- Probabilistic graphical models.
- The Multiple-Try Method and Local Optimization in Metropolis Sampling
Cited in
(26)- New perspectives on knockoffs construction
- Powerful knockoffs via minimizing reconstructability
- Robust inference with knockoffs
- Relaxing the assumptions of knockoffs by conditioning
- Causal inference in genetic trio studies
- Deep knockoffs
- FANOK: knockoffs in linear time
- Gene hunting with hidden Markov model knockoffs
- Compositional knockoff filter for high‐dimensional regression analysis of microbiome data
- Knockoff procedure for false discovery rate control in high-dimensional data streams
- A Scale-Free Approach for False Discovery Rate Control in Generalized Linear Models
- Knockoffs with side information
- Identification of microbial features in multivariate regression under false discovery rate control
- False Discovery Rate Control via Data Splitting
- Generating knockoffs via conditional independence
- A robust knockoff filter for sparse regression analysis of microbiome compositional data
- Deep latent variable models for generating knockoffs
- Controlling the false discovery rate by a latent Gaussian copula knockoff procedure
- FDR control and power analysis for high-dimensional logistic regression via Stabkoff
- False discovery rate-controlled multiple testing for union null hypotheses: a knockoff-based approach
- Conditional feature importance for mixed data
- Overview of research advance for knockoff methods
- Derandomized Truncated D-vine Copula Knockoffs with e-values to control the false discovery rate
- Knoop: practical enhancement of knockoff with over-parameterization for variable selection
- Controlling false discovery rate for mediator selection in high-dimensional data
- Knockoffs for partially exchangeable categorical covariates
This page was built for publication: Metropolized Knockoff Sampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6044631)
