Paperlane

no. 1 · Friday 23 October 2026

Sharp convergence rate of the estimation error of LASSO via the Feature Space Decomposition method

Guillaume Lecué and Zong Shang

math.ST

Abstract

In this paper, we use the Feature Space Decomposition (FSD) method to establish an explicit, non-asymptotic, instance-optimal convergence rate for the estimation error of the LASSO in the Gaussian linear regression problem for any signal, any diagonal covariance and any regularization parameter above $σ_ξ/\sqrt{N}$ where $σ_ξ$ is the noise variance and $N$ the number of data.

fields
Statistics Theory
pdf ↗ page arXiv:2610.30622 ↗