Back to Search
Start Over
Estimation in Reproducing Kernel Hilbert Spaces With Dependent Data.
- Source :
- IEEE Transactions on Information Theory; Mar2021, Vol. 67 Issue 32, p1782-1795, 14p
- Publication Year :
- 2021
-
Abstract
- This paper derives consistency results for estimation in the finite direct sum of reproducing kernel Hilbert spaces (RKHS) for dependent data. The link between penalized and constrained estimation is established. We consider the relation between topological equivalent norms for direct sums of RKHS. These norms have different implications for estimation. Estimation in a ball of the RKHS defined by these norms essentially results in estimation with a ridge and Lasso penalty, respectively. A greedy algorithm for the solution of the estimation problem under these two norms is discussed for general loss functions. [ABSTRACT FROM AUTHOR]
- Subjects :
- HILBERT space
GREEDY algorithms
Subjects
Details
- Language :
- English
- ISSN :
- 00189448
- Volume :
- 67
- Issue :
- 32
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Information Theory
- Publication Type :
- Academic Journal
- Accession number :
- 148822595
- Full Text :
- https://doi.org/10.1109/TIT.2020.3045290