Concentration estimates for the moving least-square method in learning theory (Q719353): Difference between revisions
From MaRDI portal
Set profile property. |
Set OpenAlex properties. |
||
Property / full work available at URL | |||
Property / full work available at URL: https://doi.org/10.1016/j.jat.2011.03.006 / rank | |||
Normal rank | |||
Property / OpenAlex ID | |||
Property / OpenAlex ID: W2095375944 / rank | |||
Normal rank |
Revision as of 02:15, 20 March 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Concentration estimates for the moving least-square method in learning theory |
scientific article |
Statements
Concentration estimates for the moving least-square method in learning theory (English)
0 references
10 October 2011
0 references
Moving least-square method is a classical tool in statistics, numerical analysis and approximation theory. It was studied by the author, \textit{D.-H. Xiang} and \textit{D.-X. Zhou} [ J. Approx. Theory 162, No. 3, 599--614 (2010; Zbl 1202.68325)] in a learning theory framework. In this paper the author improves the estimate for the sampling error by means of a concentration inequality, which leads to better convergence rates.
0 references
Learning theory
0 references
moving least-square method
0 references
sample error
0 references
norming condition
0 references
concentration inequality
0 references