Sparse recovery under matrix uncertainty

DOI10.1214/10-AOS793zbMath1373.62357arXiv0812.2818MaRDI QIDQ605921

Alexandre B. Tsybakov, Mathieu Rosenbaum

Publication date: 15 November 2010

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

Full work available at URL: https://arxiv.org/abs/0812.2818

zbMATH Keywords

measurement error; missing data; portfolio selection; sparsity; oracle inequalities; matrix uncertainty; errors-in-variables model; MU-selector; portfolio replication; restricted eigenvalue assumption; sign consistency

Mathematics Subject Classification ID

62F12: Asymptotic properties of parametric estimators

62J07: Ridge regression; shrinkage estimators (Lasso)

62J05: Linear regression; mixed models

62P05: Applications of statistics to actuarial sciences and financial mathematics

Related Items

An \(\{\ell_{1},\ell_{2},\ell_{\infty}\}\)-regularization approach to high-dimensional errors-in-variables models, Perturbations of measurement matrices and dictionaries in compressed sensing, Weighted \(\ell_1\)-penalized corrected quantile regression for high dimensional measurement error models, High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity, A general family of trimmed estimators for robust high-dimensional data analysis, Sparse linear models and \(l_1\)-regularized 2SLS with high-dimensional endogenous regressors and instruments, Balanced estimation for high-dimensional measurement error models, Least squares after model selection in high-dimensional sparse models, Robust subspace clustering, Pivotal estimation via square-root lasso in nonparametric regression, \(\ell_1\)-penalized quantile regression in high-dimensional sparse models, Estimation and variable selection in partial linear single index models with error-prone linear covariates

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• The Adaptive Lasso and Its Oracle Properties
• Sparse regression learning by aggregation and Langevin Monte-Carlo
• The Dantzig selector and sparsity oracle inequalities
• Some sharp performance bounds for least squares regression with \(L_1\) regularization
• The restricted isometry property and its implications for compressed sensing
• The sparsity and bias of the LASSO selection in high-dimensional linear regression
• Asymptotic equivalence for nonparametric regression with multivariate and random design
• Simultaneous analysis of Lasso and Dantzig selector
• High-dimensional generalized linear models and the lasso
• Sparsity oracle inequalities for the Lasso
• Sup-norm convergence rate and sign concentration property of Lasso and Dantzig estimators
• Aggregation for Gaussian regression
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• High-dimensional graphs and variable selection with the Lasso
• Sparse and stable Markowitz portfolios
• Decoding by Linear Programming
• Stable recovery of sparse overcomplete representations in the presence of noise
• On inverse problems with unknown operators
• Wavelet Deconvolution With Noisy Eigenvalues
• Stable signal recovery from incomplete and inaccurate measurements
• Adaptive estimation for inverse problems with noisy operators