Title :
Learning Rate of Least Square Regressions with Some Kind of Mercer Kernel
Author :
Baohui Sheng ; Liqin Duan ; Peixin Ye
Author_Institution :
Dept. of Math., Shaoxing Coll. of Arts & Sci., Shaoxing, China
Abstract :
We consider the error estimate of least square regression with data dependent hypothesis and coefficient regularization algorithms based on general kernel. When the kernel belongs to some kind of Mercer kernel, under a mild regularity condition on the regression function, we derive a dimensional-free learning rate m-1/6.
Keywords :
learning (artificial intelligence); least squares approximations; regression analysis; Mercer kernel; coefficient regularization algorithms; data dependent hypothesis; general kernel; learning rate; least square regressions; Convergence; Educational institutions; Eigenvalues and eigenfunctions; Kernel; Least squares approximation; Machine learning; Coeffi Data Dependent Hypothesis; Learning Rate Introduction; Mercer Kernel; Square Regressions; cient Regularization;
Conference_Titel :
Intelligent System Design and Engineering Application (ISDEA), 2012 Second International Conference on
Conference_Location :
Sanya, Hainan
Print_ISBN :
978-1-4577-2120-5
DOI :
10.1109/ISdea.2012.633
