Learning theory viewpoint of approximation by positive linear operators

We follow a learning theory viewpoint to study a family of learning schemes for regression related to positive linear operators in approximation theory. Such a learning scheme is generated from a random sample by a kernel function parameterized by a scaling parameter. The essential difference betwee...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers & mathematics with applications (1987) Ročník 60; číslo 12; s. 3177 - 3186
Hlavní autoři: Lv, Shaogao, Shi, Lei
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.12.2010
Témata:
Approximation
Approximation theory
Bernstein and Jackson kernels
Error analysis
Kernels
Learning
Learning theory
Linear operators
Mathematical analysis
Positive linear operator
Regression
Regression function
Sampling
Regression function
Bernstein and Jackson kernels
Approximation theory
Positive linear operator
Learning theory
ISSN:0898-1221, 1873-7668
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We follow a learning theory viewpoint to study a family of learning schemes for regression related to positive linear operators in approximation theory. Such a learning scheme is generated from a random sample by a kernel function parameterized by a scaling parameter. The essential difference between this algorithm and the classical approximation schemes is the randomness of the sampling points, which breaks the condition of good distribution of sampling points often required in approximation theory. We investigate the efficiency of the learning algorithm in a regression setting and present learning rates stated in terms of the smoothness of the regression function, sizes of variances, and distances of kernel centers from regular grids. The error analysis is conducted by estimating the sample error and the approximation error. Two examples with kernel functions related to continuous Bernstein bases and Jackson kernels are studied in detail and concrete learning rates are obtained.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0898-1221
1873-7668
DOI:10.1016/j.camwa.2010.10.022