Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*

DOI10.1088/1742-5468/ac9829OpenAlexW3213347999MaRDI QIDQ5055412

Lenka Zdeborová, Bruno Loureiro, Florent Krzakala, Hugo Cui

Publication date: 13 December 2022

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.15004

zbMATH Keywords

learning theorymachine learning

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Uses Software

• Scikit

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Eigenvectors of some large sample covariance matrix ensembles
• High-dimensional asymptotics of prediction: ridge regression and classification
• Concentration of measure and isoperimetric inequalities in product spaces
• Bayesian learning for neural networks
• High-dimensional dynamics of generalization error in neural networks
• Surprises in high-dimensional ridgeless least squares interpolation
• Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
• Optimal rates for the regularized least-squares algorithm
• Acceleration of Stochastic Approximation by Averaging
• Precise Error Analysis of Regularized <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math> </inline-formula>-Estimators in High Dimensions
• When do neural networks outperform kernel methods?*
• Two Models of Double Descent for Weak Features
• Benign overfitting in linear regression
• Asymptotic learning curves of kernel methods: empirical data versus teacher–student paradigm
• Support vector machines learning noisy polynomial rules
• Ridge regression and asymptotic minimax estimation over spheres of growing dimension

This page was built for publication: Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*