Asymptotic Log-loss of Prequential Maximum Likelihood Codes

dc.creatorGrunwald, Peter
dc.creatorde Rooij, Steven
dc.date2005-02-01
dc.date.accessioned2026-07-07T08:17:44Z
dc.date.available2026-07-07T08:17:44Z
dc.descriptionWe 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.description22 pages, an abstract has been submitted to COLT 2005
dc.identifierhttps://arxiv.org/abs/cs/0502004
dc.identifierhttp://arxiv.org/abs/cs/0502004
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/134197
dc.subjectMachine Learning
dc.subjectInformation Theory
dc.subjectE.4
dc.titleAsymptotic Log-loss of Prequential Maximum Likelihood Codes
dc.typetext

Files

Collections