Sup-norm convergence rate and sign concentration property of Lasso and Dantzig estimators
arXiv:0801.4610 · doi:10.1214/08-EJS177
Abstract
We derive the convergence rate simultaneously for Lasso and Dantzig estimators in a high-dimensional linear regression model under a mutual coherence assumption on the Gram matrix of the design and two different assumptions on the noise: Gaussian noise and general noise with finite variance. Then we prove that simultaneously the thresholded Lasso and Dantzig estimators with a proper choice of the threshold enjoy a sign concentration property provided that the non-zero components of the target vector are not too small.
arXiv commentPublished in at http://dx.doi.org/10.1214/08-EJS177 the Electronic Journal of Statistics (http://www.i-journals.org/ejs/) by the Institute of Mathematical Statistics (http://www.imstat.org)
References in corpus (18)
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Rejoinder to "Least angle regression" by Efron et al
- Least Angle Regression
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- High-dimensional graphs and variable selection with the Lasso
- Simultaneous analysis of Lasso and Dantzig selector
- Lasso-type recovery of sparse representations for high-dimensional data
- High-dimensional generalized linear models and the lasso
- Sparsity oracle inequalities for the Lasso
- Aggregation for Gaussian regression
- The Dantzig selector and sparsity oracle inequalities
- Consistent selection via the Lasso for high dimensional approximating regression models
Cited by in corpus (18)
- On the conditions used to prove oracle results for the Lasso
- Least squares after model selection in high-dimensional sparse models
- Bayesian linear regression with sparse priors
- Sparse recovery under matrix uncertainty
- Calibrating nonconvex penalized regression in ultra-high dimension
- Pivotal estimation via square-root Lasso in nonparametric regression
- Honest variable selection in linear and logistic regression models via and penalization
- SPADES and mixture models
- Pac-bayesian bounds for sparse regression estimation with exponential weights
- Sparse regression algorithm for activity estimation in spectrometry
- Accuracy guarantees for L1-recovery
- Iterative Soft/Hard Thresholding with Homotopy Continuation for Sparse Recovery
- Quasi-Likelihood and/or Robust Estimation in High Dimensions
- Extensions of stability selection using subsamples of observations and covariates
- General nonexact oracle inequalities for classes with a subexponential envelope
- Randomized maximum-contrast selection: subagging for large-scale regression
- Sample average approximation with heavier tails II: localization in stochastic convex optimization and persistence results for the Lasso
- An SDP Relaxation for the Sparse Integer Least Squares Problem