High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity

DOI10.1214/12-AOS1018zbMath1257.62063arXiv1109.3714OpenAlexW2099210013MaRDI QIDQ693741

Martin J. Wainwright, Po-Ling Loh

Publication date: 10 December 2012

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

Full work available at URL: https://arxiv.org/abs/1109.3714

zbMATH Keywords

regularizationM-estimationsparse linear regression

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Estimation in multivariate analysis (62H12) Linear regression; mixed models (62J05) Numerical optimization and variational techniques (65K10) Approximation algorithms (68W25)

Related Items (89)

Greedy algorithms for prediction ⋮ On Robustness of Principal Component Regression ⋮ Nonparametric covariance estimation for mixed longitudinal studies, with applications in midlife women's health ⋮ Poisson Regression With Error Corrupted High Dimensional Features ⋮ Sparse recovery via nonconvex regularized \(M\)-estimators over \(\ell_q\)-balls ⋮ Finite sample theory for high-dimensional functional/scalar time series with applications ⋮ Robust inference of risks of large portfolios ⋮ An ensemble learning method for variable selection: application to high-dimensional data and missing values ⋮ An \(\{\ell_{1},\ell_{2},\ell_{\infty}\}\)-regularization approach to high-dimensional errors-in-variables models ⋮ On two recent nonconvex penalties for regularization in machine learning ⋮ High-dimensional regression with potential prior information on variable importance ⋮ Unnamed Item ⋮ Sparse linear models and \(l_1\)-regularized 2SLS with high-dimensional endogenous regressors and instruments ⋮ \(\ell_{0}\)-penalized maximum likelihood for sparse directed acyclic graphs ⋮ Unnamed Item ⋮ Balanced estimation for high-dimensional measurement error models ⋮ An improved algorithm for high-dimensional continuous threshold expectile model with variance heterogeneity ⋮ Adaptive Bayesian SLOPE: Model Selection With Incomplete Data ⋮ Fast and Scalable Algorithm for Detection of Structural Breaks in Big VAR Models ⋮ Inference for high dimensional linear models with error-in-variables ⋮ Calibrated zero-norm regularized LS estimator for high-dimensional error-in-variables regression ⋮ Penalised robust estimators for sparse and high-dimensional linear models ⋮ Optimal detection of sparse principal components in high dimension ⋮ Regularized estimation of high‐dimensional vector autoregressions with weakly dependent innovations ⋮ Estimating the Covariance of Fragmented and Other Related Types of Functional Data ⋮ Sharp global convergence guarantees for iterative nonconvex optimization with random data ⋮ On high-dimensional Poisson models with measurement error: hypothesis testing for nonlinear nonconvex optimization ⋮ Variable selection for high‐dimensional generalized linear model with block‐missing data ⋮ The EAS approach for graphical selection consistency in vector autoregression models ⋮ A Unified Framework for Change Point Detection in High-Dimensional Linear Models ⋮ Screening Methods for Linear Errors-in-Variables Models in High Dimensions ⋮ L ₀ -regularization for high-dimensional regression with corrupted data ⋮ Sparse estimation in high-dimensional linear errors-in-variables regression via a covariate relaxation method ⋮ Double bias correction for high-dimensional sparse additive hazards regression with covariate measurement errors ⋮ Model selection in high-dimensional noisy data: a simulation study ⋮ Kernel Ordinary Differential Equations ⋮ Weighted l₁‐Penalized Corrected Quantile Regression for High‐Dimensional Temporally Dependent Measurement Errors ⋮ UNIFORM-IN-SUBMODEL BOUNDS FOR LINEAR REGRESSION IN A MODEL-FREE FRAMEWORK ⋮ Scalable interpretable learning for multi-response error-in-variables regression ⋮ Lasso guarantees for \(\beta \)-mixing heavy-tailed time series ⋮ Multi-Task Learning with High-Dimensional Noisy Images ⋮ Sparse estimation via lower-order penalty optimization methods in high-dimensional linear regression ⋮ Concentration of measure bounds for matrix-variate data with missing values ⋮ Low-rank matrix estimation via nonconvex optimization methods in multi-response errors-in-variables regression ⋮ Optimal nonparametric testing of missing completely at random and its connections to compatibility ⋮ Multiple Change Point Detection in Reduced Rank High Dimensional Vector Autoregressive Models ⋮ Learning partial differential equations for biological transport models from noisy spatio-temporal data ⋮ Lower bounds for finding stationary points I ⋮ Optimal Sparse Linear Prediction for Block-missing Multi-modality Data Without Imputation ⋮ Unnamed Item ⋮ Confidence sets in sparse regression ⋮ Structure estimation for discrete graphical models: generalized covariance matrices and their inverses ⋮ Sparse Identification and Estimation of Large-Scale Vector AutoRegressive Moving Averages ⋮ On the uniform convergence of empirical norms and inner products, with application to causal inference ⋮ On Parameter Estimation for High Dimensional Errors-in-Variables Models ⋮ Oracle Inequalities for Local and Global Empirical Risk Minimizers ⋮ On higher order isotropy conditions and lower bounds for sparse quadratic forms ⋮ Going beyond oracle property: selection consistency and uniqueness of local solution of the generalized linear model ⋮ Norm statement considered harmful: comment on ‘evolution of unconditional dispersal in periodic environments’ ⋮ Weighted \(\ell_1\)-penalized corrected quantile regression for high dimensional measurement error models ⋮ Rejoinder ⋮ Unnamed Item ⋮ The landscape of empirical risk for nonconvex losses ⋮ Robust subspace clustering ⋮ A Tight Bound of Hard Thresholding ⋮ High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity ⋮ Covariate Selection in High-Dimensional Generalized Linear Models With Measurement Error ⋮ Rate optimal estimation and confidence intervals for high-dimensional regression with missing covariates ⋮ Penalized Estimation and Forecasting of Multiple Subject Intensive Longitudinal Data ⋮ Regularized estimation in sparse high-dimensional time series models ⋮ Kernel Knockoffs Selection for Nonparametric Additive Models ⋮ Lasso estimation for spherical autoregressive processes ⋮ Minimax Optimal Procedures for Locally Private Estimation ⋮ Inference in high dimensional linear measurement error models ⋮ Estimation of high-dimensional graphical models using regularized score matching ⋮ Rejoinder of ``Estimating structured high-dimensional covariance and precision matrices: optimal rates and adaptive estimation ⋮ Performance bounds for parameter estimates of high-dimensional linear models with correlated errors ⋮ Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees ⋮ Minimax rate-optimal estimation of high-dimensional covariance matrices with incomplete data ⋮ Fast global convergence of gradient methods for high-dimensional statistical recovery ⋮ The generalized equivalence of regularization and min-max robustification in linear mixed models ⋮ Sparse principal component analysis with missing observations ⋮ A Sparse Learning Approach to Relative-Volatility-Managed Portfolio Selection ⋮ Estimating high-dimensional covariance and precision matrices under general missing dependence ⋮ Scale calibration for high-dimensional robust regression ⋮ Unnamed Item ⋮ Unnamed Item ⋮ On consistency and sparsity for high-dimensional functional time series with application to autoregressions ⋮ Asymptotic Properties of Stationary Solutions of Coupled Nonconvex Nonsmooth Empirical Risk Minimization

Uses Software

• PDCO

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Missing values: sparse inverse covariance estimation and an extension to sparse regression
• Sparse recovery under matrix uncertainty
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
• Fast global convergence of gradient methods for high-dimensional statistical recovery
• The sparsity and bias of the LASSO selection in high-dimensional linear regression
• Lasso-type recovery of sparse representations for high-dimensional data
• Sparse permutation invariant covariance estimation
• On the conditions used to prove oracle results for the Lasso
• Simultaneous analysis of Lasso and Dantzig selector
• High-dimensional graphs and variable selection with the Lasso
• Reconstruction From Anisotropic Random Measurements
• Covariate Selection for Linear Errors-in-Variables Regression Models
• Multiplicative Errors-in-Variables Models with Applications to Recent Data Released by the U.S. Department of Energy
• Atomic Decomposition by Basis Pursuit
• Polynomial Regression and Estimating Functions in the Presence of Multiplicative Measurement Error
• Improved matrix uncertainty selector
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers

This page was built for publication: High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity