A new concentration result for regularized risk minimizers
| dc.creator | Steinwart, Ingo | |
| dc.creator | Hush, Don | |
| dc.creator | Scovel, Clint | |
| dc.date | 2006-12-27 | |
| dc.date.accessioned | 2026-07-07T08:08:31Z | |
| dc.date.available | 2026-07-07T08:08:31Z | |
| dc.description | We establish a new concentration result for regularized risk minimizers which is similar to an oracle inequality. Applying this inequality to regularized least squares minimizers like least squares support vector machines, we show that these algorithms learn with (almost) the optimal rate in some specific situations. In addition, for regression our results suggest that using the loss function $L_α(y,t)=|y-t|^α$ with $α$ near 1 may often be preferable to the usual choice of $α=2$. | |
| dc.description | Published at http://dx.doi.org/10.1214/074921706000000897 in the IMS Lecture Notes Monograph Series (http://www.imstat.org/publications/lecnotes.htm) by the Institute of Mathematical Statistics (http://www.imstat.org) | |
| dc.identifier | https://arxiv.org/abs/math/0612779 | |
| dc.identifier | http://arxiv.org/abs/math/0612779 | |
| dc.identifier | IMS Lecture Notes Monograph Series 2006, Vol. 51, 260-275 | |
| dc.identifier | doi:10.1214/074921706000000897 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/131287 | |
| dc.subject | Statistics Theory | |
| dc.title | A new concentration result for regularized risk minimizers | |
| dc.type | text |