Optimal oracle inequalities for model selection
| dc.creator | Mitchell, Charles | |
| dc.creator | van de Geer, Sara | |
| dc.date | 2008-06-25 | |
| dc.date.accessioned | 2026-07-07T12:19:41Z | |
| dc.date.available | 2026-07-07T12:19:41Z | |
| dc.description | Model selection is often performed by empirical risk minimization. The quality of selection in a given situation can be assessed by risk bounds, which require assumptions both on the margin and the tails of the losses used. Starting with examples from the 3 basic estimation problems, regression, classification and density estimation, we formulate risk bounds for empirical risk minimization under successively weakening conditions and prove them at a very general level, for general margin and power tail behavior of the excess losses. | |
| dc.description | Submitted to the Electronic Journal of Statistics (http://www.i-journals.org/ejs/) by the Institute of Mathematical Statistics (http://www.imstat.org) | |
| dc.identifier | https://arxiv.org/abs/0806.4140 | |
| dc.identifier | http://arxiv.org/abs/0806.4140 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/212841 | |
| dc.subject | Statistics Theory | |
| dc.subject | 62G05 (Primary) 62G20 (Secondary) | |
| dc.title | Optimal oracle inequalities for model selection | |
| dc.type | text |