Back to Search
Start Over
On the Rate of Convergence of Local Averaging Plug-In Classification Rules Under a Margin Condition.
- Source :
-
IEEE Transactions on Information Theory . May2007, Vol. 53 Issue 5, p1735-1742. 8p. - Publication Year :
- 2007
-
Abstract
- The rates of convergence of plug-in kernel, partitioning, and nearest neighbors classification rules are analyzed. A margin condition, which measures how quickly the a posteriori probabilities cross the decision boundary, smoothness conditions on the a posteriori probabilities, and boundedness of the feature vector are imposed. The rates of convergence of the plug-in classifiers shown in this paper are faster than previously known. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 00189448
- Volume :
- 53
- Issue :
- 5
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Information Theory
- Publication Type :
- Academic Journal
- Accession number :
- 25016740
- Full Text :
- https://doi.org/10.1109/TIT.2007.894625