On higher order isotropy conditions and lower bounds for sparse quadratic forms

DOI10.1214/15-EJS983zbMath1308.62148arXiv1405.5995MaRDI QIDQ489163

Sara van de Geer, Alan Muro

Publication date: 27 January 2015

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1405.5995

zbMATH Keywords

quadratic formsisotropycompatibilitysparsityrestricted eigenvaluetransfer principle

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07)

Related Items

On least squares estimation under heteroscedastic and heavy-tailed errors, Posterior contraction in group sparse logit models for categorical responses, Controlling the least eigenvalue of a random Gram matrix, On the interval of fluctuation of the singular values of random matrices, The lower tail of random quadratic forms with applications to ordinary least squares, Bayesian linear regression with sparse priors, Inference for high-dimensional instrumental variables regression, Oracle inequalities for high-dimensional prediction, The smallest singular value of a shifted $d$-regular random square matrix, Unnamed Item, Sparse recovery under weak moment assumptions, On tight bounds for the Lasso, Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices

Uses Software

• PDCO

Cites Work

• Unnamed Item
• Covariance estimation for distributions with \({2+\varepsilon}\) moments
• Statistics for high-dimensional data. Methods, theory and applications.
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
• Highly sparse representations from dictionaries are unique and independent of the sparseness measure
• Uniform uncertainty principle for Bernoulli and subgaussian ensembles
• A Bennett concentration inequality and its application to suprema of empirical processes
• Weak convergence and empirical processes. With applications to statistics
• On the conditions used to prove oracle results for the Lasso
• Simultaneous analysis of Lasso and Dantzig selector
• On the uniform convergence of empirical norms and inner products, with application to causal inference
• Reconstruction From Anisotropic Random Measurements
• Bounding the Smallest Singular Value of a Random Matrix Without Concentration
• Quantitative estimates of the convergence of the empirical covariance matrix in log-concave ensembles
• Atomic Decomposition by Basis Pursuit