On the conditions used to prove oracle results for the Lasso
Electronic Journal of Statistics2009Vol. 3(none)
Citations Over TimeTop 1% of 2009 papers
Abstract
Oracle inequalities and variable selection properties for the Lasso in linear models have been established under a variety of different assumptions on the design matrix. We show in this paper how the different conditions and concepts relate to each other. The restricted eigenvalue condition [2] or the slightly weaker compatibility condition [18] are sufficient for oracle results. We argue that both these conditions allow for a fairly general class of design matrices. Hence, optimality of the Lasso for prediction and estimation holds for more general situations than what it appears from coherence [5, 4] or restricted isometry [10] assumptions.
Related Papers
- A NOTE ON THE LASSO AND RELATED PROCEDURES IN MODEL SELECTION(2006)
- → Total Variation Minimization for Compressed Sensing with “Smoothly” Varying Covariates(2016)1 cited
- The LASSO for generic design matrices as a function of the relaxation parameter(2011)
- → Dual Lasso Selector(2017)1 cited