Loading...
Please wait, while we are loading the content...
Similar Documents
A support vector method for multivariate performance measures (2005)
| Content Provider | CiteSeerX |
|---|---|
| Author | Joachims, Thorsten |
| Description | Proceedings of the 22nd International Conference on Machine Learning |
| Abstract | This paper presents a Support Vector Method for optimizing multivariate nonlinear performance measures like the F1score. Taking a multivariate prediction approach, we give an algorithm with which such multivariate SVMs can be trained in polynomial time for large classes of potentially non-linear performance measures, in particular ROCArea and all measures that can be computed from the contingency table. The conventional classification SVM arises as a special case of our method. 1. |
| File Format | |
| Publisher Date | 2005-01-01 |
| Access Restriction | Open |
| Subject Keyword | Conventional Classification Svm Multivariate Nonlinear Performance Measure Particular Rocarea Support Vector Method Multivariate Svms Non-linear Performance Measure Multivariate Prediction Approach Multivariate Performance Measure Large Class Polynomial Time Contingency Table |
| Content Type | Text |
| Resource Type | Proceeding Conference Proceedings Article |
