Metric entropy in competitive on-line prediction
| dc.creator | Vovk, Vladimir | |
| dc.date | 2006-09-09 | |
| dc.date.accessioned | 2026-07-07T07:23:49Z | |
| dc.date.available | 2026-07-07T07:23:49Z | |
| dc.description | Competitive on-line prediction (also known as universal prediction of individual sequences) is a strand of learning theory avoiding making any stochastic assumptions about the way the observations are generated. The predictor's goal is to compete with a benchmark class of prediction rules, which is often a proper Banach function space. Metric entropy provides a unifying framework for competitive on-line prediction: the numerous known upper bounds on the metric entropy of various compact sets in function spaces readily imply bounds on the performance of on-line prediction strategies. This paper discusses strengths and limitations of the direct approach to competitive on-line prediction via metric entropy, including comparisons to other approaches. | |
| dc.description | 41 pages | |
| dc.identifier | https://arxiv.org/abs/cs/0609045 | |
| dc.identifier | http://arxiv.org/abs/cs/0609045 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/116126 | |
| dc.subject | Machine Learning | |
| dc.title | Metric entropy in competitive on-line prediction | |
| dc.type | text |