Optimal Feature Selection in High-Dimensional Discriminant Analysis
We consider the high-dimensional discriminant analysis problem. For this problem, different methods have been proposed and justified by establishing exact convergence rates for the classification risk, as well as the ℓ2 convergence results to the discriminative rule. However, sharp theoretical analy...
| Veröffentlicht in: | IEEE transactions on information theory. - 1998. - 61(2015), 2 vom: 01. Feb., Seite 1063-1083 |
|---|---|
| 1. Verfasser: | |
| Weitere Verfasser: | |
| Format: | Aufsatz |
| Sprache: | English |
| Veröffentlicht: |
2015
|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on information theory |
| Schlagworte: | Journal Article discriminant analysis high-dimensional statistics optimal rates of convergence variable selection |