Regularization Methods Based on the <i>L<sub>q</sub></i>-Likelihood for Linear Models with Heavy-Tailed Errors

Regularization Methods Based on the <i>L<sub>q</sub></i>-Likelihood for Linear Models with Heavy-Tailed Errors

We propose regularization methods for linear models based on the <inline-formula><math display="inline"><semantics><msub><mi>L</mi><mi>q</mi></msub></semantics></math></inline-formula>-likelihood, which is a generaliza...

Full description

Bibliographic Details
Main Author: Yoshihiro Hirose
Format: Article
Language:English
Published: MDPI AG 2020-09-01
Series:Entropy
Subjects:
least absolute shrinkage and selection operator (LASSO)
minimax concave penalty (MCP)
power function
<i>q</i>-normal distribution
smoothly clipped absolute deviation (SCAD)
sparse estimation
Online Access:https://www.mdpi.com/1099-4300/22/9/1036

Similar Items

Similar Items