On the robustness of the minimim l2 interpolator

2020/03/12 by Geoffrey Chinot, Matthieu Lerasle, Chinot, Geoffrey +1
Engineering · Mathematics · #Bounded function #Combinatorics #Discrete mathematics #Estimator #FOS: Computer and information sciences #FOS: Mathematics #Lambda #Machine Learning (stat.ML) #Mathematical analysis #Mathematics #Microwave Imaging and Scattering Analysis #Numerical methods in inverse problems #Physics #Quantum mechanics #Sigma #Sparse and Compressive Sensing Techniques #Statistics #Statistics Theory (math.ST) #Upper and lower bounds #math.ST #stat.ML #stat.TH

paper · pdf · doi:10.48550/arxiv.2003.05838

published in HAL (Le Centre pour la Communication Scientifique Directe) (Centre National de la Recherche Scientifique) · 18 pages

arxiv created 2021/01/05 · arxiv updated 2021/01/06 · openalex publication_date 2022/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

International audience

Citations

• Atomic Decomposition by Basis Pursuit
• Learning without Concentration
• Does data interpolation contradict statistical optimality?
• Reconciling modern machine learning practice and the bias-variance trade-off
• The generalization error of random features regression: Precise asymptotics and double descent curve

Related

• Fast Rates for Noisy Interpolation Require Rethinking the Effects of Inductive Bias
• Minimum ℓ₁-norm interpolators: Precise asymptotics and multiple descent
• Surprises in High-Dimensional Ridgeless Least Squares Interpolation
• Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Linear Regression
• Interpolating Predictors in High-Dimensional Factor Regression