Work

Benign Overfitting Property of the Minimum $\ell_q$ -norm Interpolant Estimator in Regression Problem via Feature Space Decomposition

Year: 2026

Type: preprint

Abstract: This paper establishes high-probability, non-asymptotic upper bounds for the population excess risk of minimum $\ell_q$-norm interpolating estimators in linear regression, valid for all $1

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.24350

Authors: Adamczak, Radosław, Lecué, Guillaume, Shang, Zong, Strzelecka, Marta

Institutions: University of Warsaw, École Supérieure des Sciences Économiques et Commerciales, 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

OpenAlex ID: W7223037400

Cites: 11

Cited by: 2

Related to: 10