For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability

DOI10.1142/S0219530522400115MaRDI QIDQ5873932zbMATH OpenOpenAlexFDO

Authors Akshay Rangamani, Lorenzo Rosasco, T. Poggio

Publication date 10 February 2023

Published in Analysis and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/s0219530522400115

zbMATH Keywords

kernel regressionhigh-dimensional statisticsoverparameterizationalgorithmic stabilityminimum-norm interpolation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• 10.1162/153244302760200704
• A revisitation of formulae for the Moore-Penrose inverse of modified matrices.
• Benign overfitting in linear regression
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
• Generalized Inversion of Modified Matrices
• Interpolation of scattered data: distance matrices and conditionally positive definite functions
• Just interpolate: kernel ``ridgeless regression can generalize
• Learnability, stability and uniform convergence
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• Reconciling modern machine-learning practice and the classical bias-variance trade-off
• Statistics for high-dimensional data. Methods, theory and applications.
• Support Vector Machines
• Surprises in high-dimensional ridgeless least squares interpolation
• The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
• The spectrum of kernel random matrices
• Theory of Classification: a Survey of Some Recent Advances
• Understanding machine learning. From theory to algorithms

Cited in

(1)

• Sample complexity bounds for the local convergence of least squares approximation

This page was built for publication: For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5873932)