Approximation by multivariate Bernstein–Durrmeyer operators and learning rates of least-squares regularized regression with multivariate polynomial kernels

Bingzheng Li

doi:10.1016/j.jat.2013.04.007

ScienceGate Book Chapters

JOURNAL ARTICLE

Approximation by multivariate Bernstein–Durrmeyer operators and learning rates of least-squares regularized regression with multivariate polynomial kernels

Bingzheng Li

Year: 2013 Journal: Journal of Approximation Theory Vol: 173 Pages: 33-55 Publisher: Elsevier BV

DOI: 10.1016/j.jat.2013.04.007

Get Full-Text PDF Get Analytical Report

Keywords:

Mathematics Reproducing kernel Hilbert space Multivariate statistics Kernel (algebra) Polynomial Polynomial kernel Hilbert space Applied mathematics Rate of convergence Variable kernel density estimation Bernstein polynomial Polynomial regression Combinatorics Kernel method Statistics Regression Mathematical analysis

Metrics

Cited By

2.37

FWCI (Field Weighted Citation Impact)

Refs

0.91

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Approximation Theory and Sequence Spaces

Physical Sciences → Mathematics → Statistics and Probability

Optimization and Variational Analysis

Physical Sciences → Computer Science → Computational Theory and Mathematics

Sparse and Compressive Sensing Techniques

Physical Sciences → Engineering → Computational Mechanics

Approximation by multivariate Bernstein–Durrmeyer operators and learning rates of least-squares regularized regression with multivariate polynomial kernels

Metrics

Citation History

Topics

Related Documents

Approximation by multivariate max-product Kantorovich-type operators and learning rates of least-squares regularized regression

Learning rates for regularized classifiers using multivariate polynomial kernels

Learning rates of least-square regularized regression with polynomial kernels

Multivariate Bernstein–Durrmeyer operators with arbitrary weight functions

Approximation by Multivariate Bernstein Operators