Constraints and Conditions: the Lasso Oracle-inequalities
Statistics Theory
2018-06-15 v3 Statistics Theory
Abstract
We study various constraints and conditions on the true coefficient vector and on the design matrix to establish non-asymptotic oracle inequalities for the prediction error, estimation accuracy and variable selection for the Lasso estimator in high dimensional sparse regression models. We review results from the literature and we provide simpler and detailed derivation for several boundedness theorems. In addition, we complement the theory with illustrated examples.
Keywords
Cite
@article{arxiv.1603.06177,
title = {Constraints and Conditions: the Lasso Oracle-inequalities},
author = {Niharika Gauraha},
journal= {arXiv preprint arXiv:1603.06177},
year = {2018}
}