Constructive Analysis for Least Squares Regression with GeneralizedK-Norm Regularization
Keyword(s):
We introduce a constructive approach for the least squares algorithms with generalizedK-norm regularization. Different from the previous studies, a stepping-stone function is constructed with some adjustable parameters in error decomposition. It makes the analysis flexible and may be extended to other algorithms. Based on projection technique for sample error and spectral theorem for integral operator in regularization error, we finally derive a learning rate.
2013 ◽
2015 ◽
Vol 135
(2)
◽
pp. 236-243
2012 ◽
Vol 61
(2)
◽
pp. 277-290
◽
2018 ◽
Vol 74
(4)
◽
pp. I_301-I_306
◽
2020 ◽
Vol 23
(1)
◽
pp. 213-226
◽