Statistical analysis of the moving least-squares method with unbounded sampling

Authors:
Fangchao He;Hong Chen;Luoqing Li
Affiliations:
-;-;-
Venue:
Information Sciences: an International Journal
Year:
2014

Citing 17
Cited 0

The covering number in learning theory

Journal of Complexity
Support Vector Machine Soft Margin Classifiers: Error Analysis

The Journal of Machine Learning Research
Learning Rates of Least-Square Regularized Regression

Foundations of Computational Mathematics
Learning Theory: An Approximation Theory Viewpoint (Cambridge Monographs on Applied & Computational Mathematics)

Learning Theory: An Approximation Theory Viewpoint (Cambridge Monographs on Applied & Computational Mathematics)
Multi-kernel regularized classifiers

Journal of Complexity
Optimal Rates for the Regularized Least-Squares Algorithm

Foundations of Computational Mathematics
Elastic-net regularization in learning theory

Journal of Complexity
Stable Moving Least-Squares

Journal of Approximation Theory
Hermite type moving-least-squares approximations

Computers & Mathematics with Applications
Moving least-square method in learning theory

Journal of Approximation Theory
Optimal learning rates for least squares regularized regression with unbounded sampling

Journal of Complexity
Full length article: Concentration estimates for the moving least-square method in learning theory

Journal of Approximation Theory
An evolutionary programming based asymmetric weighted least squares support vector machine ensemble learning methodology for software repository mining

Information Sciences: an International Journal
Capacity of reproducing kernel spaces in learning theory

IEEE Transactions on Information Theory
Generalization performance of magnitude-preserving semi-supervised ranking with graph-based regularization

Information Sciences: an International Journal
Concentration estimates for learning with unbounded sampling

Advances in Computational Mathematics
Learning theory approach to minimum error entropy criterion

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.07

Visualization

Abstract

Moving least-squares method is investigated with samples drawn from unbounded sampling processes. Convergence analysis is established by imposing incremental conditions on moments of sample output and window width. Satisfied convergence rates are derived by means of projection operator and some concentration inequalities.