The phase diagram of kernel interpolation in large dimensions

DOI10.1093/BIOMET/ASAE057MaRDI QIDQ6915837zbMATH OpenFDO

Authors Haobo Zhang, Weihao Lu, Qian Lin

Publication date 15 October 2025

Published in Biometrika (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1093/BIOMET/ASAE057

zbMATH Keywords

benign overfittinghigh dimensionkernel interpolationlower boundminimax optimality

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• Benign overfitting in linear regression
• Generalization error of random feature and kernel methods: hypercontractivity and kernel matrix concentration
• Just interpolate: kernel ``ridgeless regression can generalize
• Mercer's theorem on general domains: on the interaction between measures, kernels, and RKHSs
• On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions
• Optimal rates for the regularized least-squares algorithm
• Reconciling modern machine-learning practice and the classical bias-variance trade-off
• Sobolev norm learning rates for regularized least-squares algorithms
• Strictly and non-strictly positive definite functions on spheres
• Support Vector Machines

This page was built for publication: The phase diagram of kernel interpolation in large dimensions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6915837)