Convergence Rate for <inline-formula> <tex-math notation="LaTeX">$l^{q}$ </tex-math></inline-formula>-Coefficient Regularized Regression With Non-i.i.d. Sampling

Convergence Rate for <inline-formula> <tex-math notation="LaTeX">$l^{q}$ </tex-math></inline-formula>-Coefficient Regularized Regression With Non-i.i.d. Sampling

Many learning algorithms use hypothesis spaces which are trained from samples, but little theoretical work has been devoted to the study of these algorithms. In this paper, we show that mathematical analysis for the kernel-based coefficient least squares for regression with l<sup>q</sup>...

Full description

Bibliographic Details
Main Authors: Qin Guo, Peixin Ye, Binlei Cai
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Coefficient-based regularized regression
drift error
learning rate
mixing sequence
uniform concentration inequality
Online Access:https://ieeexplore.ieee.org/document/8319967/

Internet

https://ieeexplore.ieee.org/document/8319967/

Similar Items