Prediction Error Bounds for Linear Regression With the TREX
Statistics Theory
2018-01-08 v1 Statistics Theory
Abstract
The TREX is a recently introduced approach to sparse linear regression. In contrast to most well-known approaches to penalized regression, the TREX can be formulated without the use of tuning parameters. In this paper, we establish the first known prediction error bounds for the TREX. Additionally, we introduce extensions of the TREX to a more general class of penalties, and we provide a bound on the prediction error in this generalized setting. These results deepen the understanding of TREX from a theoretical perspective and provide new insights into penalized regression in general.
Cite
@article{arxiv.1801.01394,
title = {Prediction Error Bounds for Linear Regression With the TREX},
author = {Jacob Bien and Irina Gaynanova and Johannes Lederer and Christian Müller},
journal= {arXiv preprint arXiv:1801.01394},
year = {2018}
}