Covariate assisted screening and estimation

DOI10.1214/14-AOS1243zbMATH Open1310.62085arXiv1205.4645OpenAlexW2134838351WikidataQ24288829 ScholiaQ24288829MaRDI QIDQ482879FDOQ482879

Authors: Zheng Tracy Ke, Jiashun Jin, Jianqing Fan 

Publication date: 6 January 2015

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: Consider a linear model $$, where $X=X_{n,p}$ and $zsimN(0,I_n)$. The vector $$ is unknown but is sparse in the sense that most of its coordinates are $0$. The main interest is to separate its nonzero coordinates from the zero ones (i.e., variable selection). Motivated by examples in long-memory time series (Fan and Yao [Nonlinear Time Series: Nonparametric and Parametric Methods (2003) Springer]) and the change-point problem (Bhattacharya [In Change-Point Problems (South Hadley, MA, 1992) (1994) 28-56 IMS]), we are primarily interested in the case where the Gram matrix $G=X^{\prime }X$ is nonsparse but sparsifiable by a finite order linear filter. We focus on the regime where signals are both rare and weak so that successful variable selection is very challenging but is still possible. We approach this problem by a new procedure called the covariate assisted screening and estimation (CASE). CASE first uses a linear filtering to reduce the original setting to a new regression model where the corresponding Gram (covariance) matrix is sparse. The new covariance matrix induces a sparse graph, which guides us to conduct multivariate screening without visiting all the submodels. By interacting with the signal sparsity, the graph enables us to decompose the original problem into many separated small-size subproblems (if only we know where they are!). Linear filtering also induces a so-called problem of information leakage, which can be overcome by the newly introduced patching technique. Together, these give rise to CASE, which is a two-stage screen and clean [Fan and Song Ann. Statist. 38 (2010) 3567-3604; Wasserman and Roeder Ann. Statist. 37 (2009) 2178-2201] procedure, where we first identify candidates of these submodels by patching and screening, and then re-examine each candidate to remove false positives.

Full work available at URL: https://arxiv.org/abs/1205.4645

Recommendations

• Optimality of Graphlet Screening in High Dimensional Variable Selection
• Variable screening for high dimensional time series
• Sure Independence Screening for Ultrahigh Dimensional Feature Space
• Sparse covariance thresholding for high-dimensional variable selection
• Exponential screening and optimal rates of sparse estimation

zbMATH Keywords

variable selectionHamming distancesparsityphase diagramasymptotic minimaxitygraph of least favorables (GOLF)graph of strong dependence (GOSD)multivariate screeningrare and weak signal model

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Linear regression; mixed models (62J05) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Ridge regression; shrinkage estimators (Lasso) (62J07) Minimax procedures in statistical decision theory (62C20)

Cites Work

• Sure independence screening in generalized linear models with NP-dimensionality
• Nearly unbiased variable selection under minimax concave penalty
• The Adaptive Lasso and Its Oracle Properties
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Title not available (Why is that?)
• High-dimensional graphs and variable selection with the Lasso
• Title not available (Why is that?)
• Title not available (Why is that?)
• Sparse inverse covariance estimation with the graphical lasso
• Nonlinear time series. Nonparametric and parametric methods
• Higher criticism thresholding: Optimal feature selection when useful features are rare and weak
• Scaled sparse linear regression
• Title not available (Why is that?)
• Multiple Change-Point Estimation With a Total Variation Penalty
• Circular binary segmentation for the analysis of array-based DNA copy number data
• The screening and ranking algorithm to detect DNA copy number variations
• High-dimensional variable selection
• Detecting simultaneous change points in multiple sequences
• Spatial smoothing and hot spot detection for CGH data using the fused lasso
• Optimality of Graphlet Screening in High Dimensional Variable Selection
• UPS delivers optimal phase diagram in high-dimensional variable selection
• Uncertainty principles and ideal atomic decomposition
• Covariate assisted screening and estimation
• Title not available (Why is that?)
• Title not available (Why is that?)
• Broadband log-periodogram regression of time series with long-range dependence
• Uncertainty Principles and Signal Recovery
• Strong oracle optimality of folded concave penalized estimation
• Near-ideal model selection by \(\ell _{1}\) minimization
• On the Correlation Matrix of the Discrete Fourier Transform and the Fast Solution of Large Toeplitz Systems for Long-Memory Time Series

Cited In (10)

• The Kendall interaction filter for variable interaction screening in high dimensional classification problems
• Covariate assisted screening and estimation
• Inference for sparse linear regression based on the leave-one-covariate-out solution path
• On sufficient variable screening using log odds ratio filter
• Variable selection in functional regression models: a review
• Covariate Information Number for Feature Screening in Ultrahigh-Dimensional Supervised Problems
• Adaptive Sparse Estimation With Side Information
• Which bridge estimator is the best for variable selection?
• Higher criticism for large-scale inference, especially for rare and weak effects
• High-dimensional variable screening under multicollinearity

Uses Software

• glasso
• ScreenClean

This page was built for publication: Covariate assisted screening and estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q482879)