English

High-dimensional additive hazard models and the Lasso

Statistics Theory 2012-03-06 v2 Statistics Theory

Abstract

We consider a general high-dimensional additive hazard model in a non-asymptotic setting, including regression for censored-data. In this context, we consider a Lasso estimator with a fully data-driven 1\ell_1 penalization, which is tuned for the estimation problem at hand. We prove sharp oracle inequalities for this estimator. Our analysis involves a new "data-driven" Bernstein's inequality, that is of independent interest, where the predictable variation is replaced by the optional variation.

Keywords

Cite

@article{arxiv.1106.4662,
  title  = {High-dimensional additive hazard models and the Lasso},
  author = {Séphane Gaïffas and Agathe Guilloux},
  journal= {arXiv preprint arXiv:1106.4662},
  year   = {2012}
}
R2 v1 2026-06-21T18:26:25.919Z