Approximation of the Two-Part MDL Code

Simple item page
dc.creatorAdriaans, Pieter
dc.creatorVitanyi, Paul
dc.date2006-12-19
dc.date2008-09-15
dc.date.accessioned2026-07-07T10:02:36Z
dc.date.available2026-07-07T10:02:36Z
dc.descriptionApproximation of the optimal two-part MDL code for given data, through successive monotonically length-decreasing two-part MDL codes, has the following properties: (i) computation of each step may take arbitrarily long; (ii) we may not know when we reach the optimum, or whether we will reach the optimum at all; (iii) the sequence of models generated may not monotonically improve the goodness of fit; but (iv) the model associated with the optimum has (almost) the best goodness of fit. To express the practically interesting goodness of fit of individual models for individual data sets we have to rely on Kolmogorov complexity.
dc.description14 pages, LaTeX, no figures, IEEE Trans Inform. Th., to appear
dc.identifierhttps://arxiv.org/abs/cs/0612095
dc.identifierhttp://arxiv.org/abs/cs/0612095
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/169030
dc.subjectMachine Learning
dc.subjectArtificial Intelligence
dc.subjectInformation Theory
dc.subjectE.4; I.2.6; I.5
dc.titleApproximation of the Two-Part MDL Code
dc.typetext

Files

Collections

arXiv