Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4615129 | Journal of Mathematical Analysis and Applications | 2015 | 19 Pages |
Abstract
In this paper, we consider the least squares regression algorithm with a generalized coefficient regularization term. A novel error decomposition involving a constructive stepping-stone function is introduced. By choosing appropriate parameters for the constructive function we finally derive a satisfactory learning rate under some condition for the goal function and capacity of the hypothesis space.
Related Topics
Physical Sciences and Engineering
Mathematics
Analysis
Authors
Weilin Nie, Cheng Wang,