Robust kernel-based gradient descent with random features

DOI10.1007/S10444-025-10263-7MaRDI QIDQ6879205zbMATH OpenFDO

Authors Qi Hong, Zheng-Chu Guo

Publication date 2 January 2026

Published in Advances in Computational Mathematics (Search for Journal in Brave)

zbMATH Keywords

learning theoryreproducing kernel Hilbert spacerobust regressiongradient descentrandom features

Mathematics Subject Classification ID

General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• An introduction to matrix concentration inequalities
• Breakdown points of Cauchy regression-scale estimators
• Correntropy: Properties and Applications in Non-Gaussian Signal Processing
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Gradient descent for robust kernel-based regression
• Learning Theory
• Learning theory of distributed spectral algorithms
• Learning with the maximum correntropy criterion induced losses for regression
• Norm Inequalities Equivalent to Heinz Inequality
• On some extensions of Bernstein's inequality for self-adjoint operators
• On the equivalence between kernel quadrature rules and random feature expansions
• Online learning algorithms
• Optimal rates for coefficient-based regularized regression
• Optimal rates for regularization of statistical inverse learning problems
• Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
• Optimal rates for the regularized least-squares algorithm
• Optimality of robust online learning
• Robust regression using iteratively reweighted least-squares
• Support Vector Machines
• The Barron space and the flow-induced function spaces for neural network models
• The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve

This page was built for publication: Robust kernel-based gradient descent with random features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6879205)