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...
Principais autores: | Lippert, Ross, Rifkin, Ryan |
---|---|
Idioma: | en_US |
Publicado em: |
2005
|
Assuntos: | |
Acesso em linha: | http://hdl.handle.net/1721.1/30577 |
Registros relacionados
-
Notes on Regularized Least Squares
por: Rifkin, Ryan M., et al.
Publicado em: (2007) -
Bagging Regularizes
por: Poggio, Tomaso, et al.
Publicado em: (2004) -
Fast Rates for Regularized Least-squares Algorithm
por: Caponnetto, Andrea, et al.
Publicado em: (2005) -
GURLS: a Toolbox for Regularized Least Squares Learning
por: Tacchetti, Andrea, et al.
Publicado em: (2012) -
Regularization Total Least Squares and Randomized Algorithms
por: Zhanshan Yang, et al.
Publicado em: (2024-06-01)