Support recovery and sup-norm convergence rates for sparse pivotal estimation
Machine Learning
2020-09-04 v3 Machine Learning
Optimization and Control
Abstract
In high dimensional sparse regression, pivotal estimators are estimators for which the optimal regularization parameter is independent of the noise level. The canonical pivotal estimator is the square-root Lasso, formulated along with its derivatives as a "non-smooth + non-smooth" optimization problem. Modern techniques to solve these include smoothing the datafitting term, to benefit from fast efficient proximal algorithms. In this work we show minimax sup-norm convergence rates for non smoothed and smoothed, single task and multitask square-root Lasso-type estimators. Thanks to our theoretical analysis, we provide some guidelines on how to set the smoothing hyperparameter, and illustrate on synthetic data the interest of such guidelines.
Keywords
Cite
@article{arxiv.2001.05401,
title = {Support recovery and sup-norm convergence rates for sparse pivotal estimation},
author = {Mathurin Massias and Quentin Bertrand and Alexandre Gramfort and Joseph Salmon},
journal= {arXiv preprint arXiv:2001.05401},
year = {2020}
}