 |
|
 |
|
|
|
|
|
| HAL: hal-00630476, version 1 |
| Detailed view |  Export this paper |
|
|
| International Conference on Machine Learning, États-Unis (2011) |
|
|
|
|
| Minimax Learning Rates for Bipartite Ranking and Plug-in Rules |
|
|
| Stéphan Clémençon 1Sylvain Robbiano 1 |
|
|
| (2011-06-27) |
|
|
|
| While it is now well-known in the standard binary classi cation setup, that, under suitable margin assumptions and complexity conditions on the regression function, fast or even super-fast rates can be achieved by plug-in classi ers, no result of this nature has been proved yet in the context of bipartite ranking, though akin to that of classi cation. It is the main purpose of the present paper to investigate this issue. Viewing bipartite ranking as a nested continuous collection of cost-sensitive classi cation problems, we exhibit a global low noise condition under which certain plug-in ranking rules can be shown to achieve fast (but not super-fast) rates, establishing thus minimax upper bounds for the excess of ranking risk. |
|
|
|
|
|
|
|
|
|
|
|
| 1: | Laboratoire Traitement et Communication de l'Information [Paris] (LTCI) |
|
|
|
Télécom ParisTech – CNRS : UMR5141 |
|
|
|
|
|
|
|
|
|
| Subject | : | Statistics/Machine Learning |
|
|
| Ranking – Minimax – Plug-in – Margin assumption |
|
|
|
| Attached file list to this document: | |||||
|
|||||
|
|
|
| hal-00630476, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00630476 | |
| oai:hal.archives-ouvertes.fr:hal-00630476 | |
| From: Sylvain Robbiano | |
| Submitted on: Monday, 10 October 2011 11:07:10 | |
| Updated on: Tuesday, 11 October 2011 09:47:32 | |
