Asymptotic Log-loss of Prequential Maximum Likelihood Codes
| dc.creator | Grunwald, Peter | |
| dc.creator | de Rooij, Steven | |
| dc.date | 2005-02-01 | |
| dc.date.accessioned | 2026-07-07T08:17:44Z | |
| dc.date.available | 2026-07-07T08:17:44Z | |
| dc.description | We analyze the Dawid-Rissanen prequential maximum likelihood codes relative to one-parameter exponential family models M. If data are i.i.d. according to an (essentially) arbitrary P, then the redundancy grows at rate c/2 ln n. We show that c=v1/v2, where v1 is the variance of P, and v2 is the variance of the distribution m* in M that is closest to P in KL divergence. This shows that prequential codes behave quite differently from other important universal codes such as the 2-part MDL, Shtarkov and Bayes codes, for which c=1. This behavior is undesirable in an MDL model selection setting. | |
| dc.description | 22 pages, an abstract has been submitted to COLT 2005 | |
| dc.identifier | https://arxiv.org/abs/cs/0502004 | |
| dc.identifier | http://arxiv.org/abs/cs/0502004 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/134197 | |
| dc.subject | Machine Learning | |
| dc.subject | Information Theory | |
| dc.subject | E.4 | |
| dc.title | Asymptotic Log-loss of Prequential Maximum Likelihood Codes | |
| dc.type | text |