Reconstruction From Anisotropic Random Measurements
From MaRDI portal
Abstract: Random matrices are widely used in sparse recovery problems, and the relevant properties of matrices with i.i.d. entries are well understood. The current paper discusses the recently introduced Restricted Eigenvalue (RE) condition, which is among the most general assumptions on the matrix, guaranteeing recovery. We prove a reduction principle showing that the RE condition can be guaranteed by checking the restricted isometry on a certain family of low-dimensional subspaces. This principle allows us to establish the RE condition for several broad classes of random matrices with dependent entries, including random matrices with subgaussian rows and non-trivial covariance structure, as well as matrices with independent rows, and uniformly bounded entries.
Cited in
(52)- Regularized estimation in sparse high-dimensional time series models
- Significance testing in non-sparse high-dimensional linear models
- On the prediction loss of the Lasso in the partially labeled setting
- Folded concave penalized sparse linear regression: sparsity, statistical performance, and algorithmic theory for local solutions
- High-dimensional simultaneous inference with the bootstrap
- Debiasing the Lasso: optimal sample size for Gaussian designs
- Regret lower bound and optimal algorithm for high-dimensional contextual linear bandit
- Design of c-optimal experiments for high-dimensional linear models
- Adaptive estimation in multivariate response regression with hidden variables
- Inference for high-dimensional instrumental variables regression
- Lasso guarantees for \(\beta \)-mixing heavy-tailed time series
- Quasi-Bayesian estimation of large Gaussian graphical models
- Prediction and estimation consistency of sparse multi-class penalized optimal scoring
- Sorted concave penalized regression
- Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
- On model selection consistency of regularized M-estimators
- RIPless compressed sensing from anisotropic measurements
- Estimation and variable selection with exponential weights
- On the uniform convergence of empirical norms and inner products, with application to causal inference
- Regularity properties for sparse regression
- An analysis of penalized interaction models
- Linear hypothesis testing in dense high-dimensional linear models
- The lower tail of random quadratic forms with applications to ordinary least squares
- Sparse model uncertainties in compressed sensing with application to convolutions and sporadic communication
- Improved recovery guarantees for phase retrieval from coded diffraction patterns
- On the stability of sparse convolutions
- Orientation of anisotropic random fields and images
- Non-negative least squares for high-dimensional linear models: consistency and sparse recovery without regularization
- Dynamic pricing in high-dimensions
- On higher order isotropy conditions and lower bounds for sparse quadratic forms
- Robust inference on average treatment effects with possibly more covariates than observations
- High-dimensional interactions detection with sparse principal Hessian matrix
- scientific article; zbMATH DE number 7370544 (Why is no real title available?)
- Generalized regression estimators with high-dimensional covariates
- Fixed effects testing in high-dimensional linear mixed models
- Sparse recovery under weak moment assumptions
- An efficient two step algorithm for high dimensional change point regression models without grid search
- Anomaly Detection and Reconstruction From Random Projections
- A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers
- Estimating structured high-dimensional covariance and precision matrices: optimal rates and adaptive estimation
- Joint association and classification analysis of multi‐view data
- Concentration of measure bounds for matrix-variate data with missing values
- High-dimensional composite quantile regression: optimal statistical guarantees and fast algorithms
- An alternative to synthetic control for models with many covariates under sparsity
- Robust recovery of Robinson property in L^p-graphons: a cut-norm approach
- Minimax Quasi-Bayesian Estimation in Sparse Canonical Correlation Analysis via a Rayleigh Quotient Function
- High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
- Sparse estimation and inference for prediction-powered semi-supervised linear regression
- Sharp optimality of sparse group LASSO and SLOPE under weaker assumptions
- A note on the minimax risk of sparse linear regression
- Fast global convergence of gradient methods for high-dimensional statistical recovery
- A shrinkage principle for heavy-tailed data: high-dimensional robust low-rank matrix recovery
This page was built for publication: Reconstruction From Anisotropic Random Measurements
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2989184)
