Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

Strong asymptotic assertions for discrete MDL in regression and classification

Simple item page
dc.contributor.authorPoland, Jan
dc.contributor.authorHutter, Marcus
dc.date.accessioned2015-09-01T04:43:28Z
dc.date.available2015-09-01T04:43:28Z
dc.date.issued2005-02
dc.description.abstractWe study the properties of the MDL (or maximum penalized complexity) estimator for Regression and Classification, where the underlying model class is countable. We show in particular a finite bound on the Hellinger losses under the only assumption that there is a ``true'' model contained in the class. This implies almost sure convergence of the predictive distribution to the true one at a fast rate. It corresponds to Solomonoff's central theorem of universal induction, however with a bound that is exponentially larger.en_AU
dc.identifier.issn0929-0672en_AU
dc.identifier.urihttp://hdl.handle.net/1885/15051
dc.publisherUniversity of Twenteen_AU
dc.relation.ispartofProceedings of the 14th Dutch-Belgium Conference on Machine Learning Benelearn'05en_AU
dc.rights© The Author(s)en_AU
dc.subjectRegressionen_AU
dc.subjectClassificationen_AU
dc.subjectSequence Predictionen_AU
dc.subjectMachine Learningen_AU
dc.subjectMinimum Description Lengthen_AU
dc.subjectBayes Mixtureen_AU
dc.titleStrong asymptotic assertions for discrete MDL in regression and classificationen_AU
dc.typeConference paperen_AU
local.bibliographicCitation.lastpage72en_AU
local.bibliographicCitation.startpage67en_AU
local.contributor.affiliationHutter, M., Research School of Computer Science, The Australian National Universityen_AU
local.contributor.authoruidu4350841en_AU
local.type.statusAccepted Versionen_AU

Downloads

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Poland and Hutter Strong Asymptotic Assertions 2005.pdf
Size:
175.8 KB
Format:
Adobe Portable Document Format
Description:
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
884 B
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ANU Research Publications

DSpace software copyright © 2002-2026 LYRASIS