Sparse recovery with unknown variance: a LASSO-type approach

01/02/2011
by   Stéphane Chrétien, et al.
0

We address the issue of estimating the regression vector β in the generic s-sparse linear model y = Xβ+z, with β∈^p, y∈^n, z∼ N(0,^2 I) and p> n when the variance ^2 is unknown. We study two LASSO-type methods that jointly estimate β and the variance. These estimators are minimizers of the ℓ_1 penalized least-squares functional, where the relaxation parameter is tuned according to two different strategies. In the first strategy, the relaxation parameter is of the order σ√( p), where σ^2 is the empirical variance. running only a few successive LASSO instances with relaxation parameter. In the second strategy, the relaxation parameter is chosen so as to enforce a trade-off between the fidelity and the penalty terms at optimality. For both estimators, our assumptions are similar to the ones proposed by Candès and Plan in Ann. Stat. (2009), for the case where ^2 is known. We prove that our estimators ensure exact recovery of the support and sign pattern of β with high probability. We present simulations results showing that the first estimator enjoys nearly the same performances in practice as the standard LASSO (known variance case) for a wide range of the signal to noise ratio. Our second estimator is shown to outperform both in terms of false detection, when the signal to noise ratio is low.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/06/2017

Estimating the error variance in a high-dimensional linear model

The lasso has been studied extensively as a tool for estimating the coef...
research
05/14/2018

Model selection with lasso-zero: adding straw to the haystack to better find needles

The high-dimensional linear model y = X β^0 + ϵ is considered and the fo...
research
11/03/2010

The Lasso under Heteroscedasticity

The performance of the Lasso is well understood under the assumptions of...
research
08/29/2017

Improved Support Recovery Guarantees for the Group Lasso With Applications to Structural Health Monitoring

This paper considers the problem of estimating an unknown high dimension...
research
07/19/2023

Pattern Recovery in Penalized and Thresholded Estimation and its Geometry

We consider the framework of penalized estimation where the penalty term...
research
04/16/2013

Learning Heteroscedastic Models by Convex Programming under Group Sparsity

Popular sparse estimation methods based on ℓ_1-relaxation, such as the L...
research
06/22/2023

Outlier-robust Estimation of a Sparse Linear Model Using Invexity

In this paper, we study problem of estimating a sparse regression vector...

Please sign up or login with your details

Forgot password? Click here to reset