Work

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

Year: 2026

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30622

Authors: Lecué, Guillaume, Shang, Zong

Institutions: École Supérieure des Sciences Économiques et Commerciales, Georgia Institute of Technology, Centre de Recherche en Économie et Statistique, Institut Polytechnique de Paris, ENSAE Paris

Language: English

Topic: Statistical Methods and Inference

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: green

Funders: Institut Polytechnique de Paris, Core Research for Evolutional Science and Technology

OpenAlex ID: W7223261354

Cites: 17

Cited by: 1

Related to: 10