Skip navigation
Skip navigation

MDL convergence speed for Bernoulli sequences

Poland, Jan; Hutter, Marcus

Description

The Minimum Description Length principle for online sequence estimation/prediction in a proper learning setup is studied. If the underlying model class is discrete, then the total expected square loss is a particularly interesting performance measure: (a) this quantity is finitely bounded, implying convergence with probability one, and (b) it additionally specifies the convergence speed. For MDL, in general one can only have loss bounds which are finite but exponentially larger than those for...[Show more]

CollectionsANU Research Publications
Date published: 2006-06
Type: Journal article
URI: http://hdl.handle.net/1885/15030
Source: Statistics and Computing
DOI: 10.1007/s11222-006-6746-3

Download

File Description SizeFormat Image
Poland and Hutter MDL Convergence Speed 2006.pdf308.92 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator