Learning rates of regularized regression on the unit sphere (Q365838): Difference between revisions
From MaRDI portal
Created a new Item |
Changed an Item |
||
Property / author | |||
Property / author: Feilong Cao / rank | |||
Normal rank | |||
Property / author | |||
Property / author: Shao-Bo Lin / rank | |||
Normal rank | |||
Property / author | |||
Property / author: Zong Ben Xu / rank | |||
Normal rank | |||
Property / review text | |||
This paper studies least square regularized regression learning algorithms with spherical harmonics kernels on the unit sphere. The learning error is decomposed into sample error and regularized error. To estimate the regularized error, the best approximation operator and the Jackson-type inequality are introduced. The other interesting point is that the dimension of hypothesis space charges with the size of samples. Satisfying error bound and learning rate are deduced by the covering number technique. | |||
Property / review text: This paper studies least square regularized regression learning algorithms with spherical harmonics kernels on the unit sphere. The learning error is decomposed into sample error and regularized error. To estimate the regularized error, the best approximation operator and the Jackson-type inequality are introduced. The other interesting point is that the dimension of hypothesis space charges with the size of samples. Satisfying error bound and learning rate are deduced by the covering number technique. / rank | |||
Normal rank | |||
Property / reviewed by | |||
Property / reviewed by: Hongwei Sun / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 68T05 / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 62J02 / rank | |||
Normal rank | |||
Property / zbMATH DE Number | |||
Property / zbMATH DE Number: 6207059 / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
sphere | |||
Property / zbMATH Keywords: sphere / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
regularized regression | |||
Property / zbMATH Keywords: regularized regression / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
spherical harmonics kernel | |||
Property / zbMATH Keywords: spherical harmonics kernel / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
rate of convergence | |||
Property / zbMATH Keywords: rate of convergence / rank | |||
Normal rank |
Revision as of 12:37, 28 June 2023
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Learning rates of regularized regression on the unit sphere |
scientific article |
Statements
Learning rates of regularized regression on the unit sphere (English)
0 references
9 September 2013
0 references
This paper studies least square regularized regression learning algorithms with spherical harmonics kernels on the unit sphere. The learning error is decomposed into sample error and regularized error. To estimate the regularized error, the best approximation operator and the Jackson-type inequality are introduced. The other interesting point is that the dimension of hypothesis space charges with the size of samples. Satisfying error bound and learning rate are deduced by the covering number technique.
0 references
sphere
0 references
regularized regression
0 references
spherical harmonics kernel
0 references
rate of convergence
0 references