Error Analysis of Least-Squares <inline-formula> <tex-math notation="LaTeX">$l^{^{q}}$ </tex-math></inline-formula>-Regularized Regression Learning Algorithm With the Non-Identical and Dependent Samples

Error Analysis of Least-Squares <inline-formula> <tex-math notation="LaTeX">$l^{^{q}}$ </tex-math></inline-formula>-Regularized Regression Learning Algorithm With the Non-Identical and Dependent Samples

The selection of the penalty functional is critical for the performance of a regularized learning algorithm, and thus lq-regularizer (1 &#x2264; q &#x2264; 2) deserves special attention. We consider the regularized least-squares regression learning algorithm for the non-identical and weakly...

Full description

Bibliographic Details
Main Authors: Qin Guo, Peixin Ye
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Regression function
empirical covering number
drift error
blocking technique
learning rate
Online Access:https://ieeexplore.ieee.org/document/8425633/

Internet

https://ieeexplore.ieee.org/document/8425633/

Similar Items