Concentration estimates for the moving least-square method in learning theory

DOI10.1016/j.jat.2011.03.006zbMath1237.68108MaRDI QIDQ719353

Hong-Yan Wang

Publication date: 10 October 2011

Published in: Journal of Approximation Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jat.2011.03.006

zbMATH Keywords

concentration inequality; Learning theory; sample error; moving least-square method; norming condition

Mathematics Subject Classification ID

68Q32: Computational learning theory

93E24: Least squares and related methods for stochastic control systems

Related Items

Statistical analysis of the moving least-squares method with unbounded sampling, Moving quantile regression, Learning performance of regularized moving least square regression

Cites Work

• Unnamed Item
• Multi-kernel regularized classifiers
• Moving least-square method in learning theory
• High order Parzen windows and randomized sampling
• The covering number in learning theory
• Weak convergence and empirical processes. With applications to statistics
• Regularization networks and support vector machines
• Statistical performance of support vector machines
• ONLINE REGRESSION WITH VARYING GAUSSIANS AND NON-IDENTICAL DISTRIBUTIONS
• SVM LEARNING AND L^p APPROXIMATION BY GAUSSIANS ON RIEMANNIAN MANIFOLDS
• Learning Theory
• Support Vector Machines
• Capacity of reproducing kernel spaces in learning theory
• ONLINE LEARNING WITH MARKOV SAMPLING
• Neural Network Learning