Competing with wild prediction rules
| dc.creator | Vovk, Vladimir | |
| dc.date | 2005-12-14 | |
| dc.date | 2006-01-25 | |
| dc.date.accessioned | 2026-07-07T06:53:50Z | |
| dc.date.available | 2026-07-07T06:53:50Z | |
| dc.description | We consider the problem of on-line prediction competitive with a benchmark class of continuous but highly irregular prediction rules. It is known that if the benchmark class is a reproducing kernel Hilbert space, there exists a prediction algorithm whose average loss over the first N examples does not exceed the average loss of any prediction rule in the class plus a "regret term" of O(N^(-1/2)). The elements of some natural benchmark classes, however, are so irregular that these classes are not Hilbert spaces. In this paper we develop Banach-space methods to construct a prediction algorithm with a regret term of O(N^(-1/p)), where p is in [2,infty) and p-2 reflects the degree to which the benchmark class fails to be a Hilbert space. | |
| dc.description | 28 pages, 3 figures | |
| dc.identifier | https://arxiv.org/abs/cs/0512059 | |
| dc.identifier | http://arxiv.org/abs/cs/0512059 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/105732 | |
| dc.subject | Machine Learning | |
| dc.subject | I.2.6 | |
| dc.title | Competing with wild prediction rules | |
| dc.type | text |