Asymptotics of Gaussian Regularized Least-Squares
We consider regularized least-squares (RLS) with a Gaussian kernel. Weprove that if we let the Gaussian bandwidth $\sigma \rightarrow\infty$ while letting the regularization parameter $\lambda\rightarrow 0$, the RLS solution tends to a polynomial whose order iscontrolled by the relative rates of dec...
Main Authors: | Lippert, Ross, Rifkin, Ryan |
---|---|
Language: | en_US |
Published: |
2005
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/30577 |
Similar Items
-
Notes on Regularized Least Squares
by: Rifkin, Ryan M., et al.
Published: (2007) -
Bagging Regularizes
by: Poggio, Tomaso, et al.
Published: (2004) -
Fast Rates for Regularized Least-squares Algorithm
by: Caponnetto, Andrea, et al.
Published: (2005) -
MDAKRLS: Predicting human microbe-disease association based on Kronecker regularized least squares and similarities
by: Da Xu, et al.
Published: (2021-02-01) -
Empirical Effective Dimension and Optimal Rates for Regularized Least Squares Algorithm
by: Caponnetto, Andrea, et al.
Published: (2005)