Convergence analysis for complementary-label learning with kernel ridge regression

DOI10.1007/S11766-024-5173-6MaRDI QIDQ6636868zbMATH OpenFDO

Authors Weilin Nie, Cheng Wang, Zhonghua Xie

Publication date 12 November 2024

Published in Applied Mathematics. Series B (English Edition) (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S11766-024-5173-6

zbMATH Keywords

reproducing kernel Hilbert spaceserror analysispartial label learningmultiple complementary-label learning

Mathematics Subject Classification ID

General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Recommendations

• Tackling biased complementary label learning with large margin
• Distributed semi-supervised learning with kernel ridge regression
• Convergence rate of semi-supervised gradient learning algorithms
• Learning a classifier when the labeling is known
• Generalization errors of Laplacian regularized least squares regression

Cites work

• Classification with Gaussians and convex loss
• ERM learning algorithm for multi-class classification
• Learning Theory
• Learning from partial labels
• Learning rates of least-square regularized regression
• On the mathematical foundations of learning
• Probability Inequalities for the Sum of Independent Random Variables
• Quantitative convergence analysis of kernel based large-margin unified machines
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• The covering number in learning theory

Cited in

(1)

• Tackling biased complementary label learning with large margin

This page was built for publication: Convergence analysis for complementary-label learning with kernel ridge regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6636868)