Skip navigation
Skip navigation

On the Convergence Speed of MDL Predictions for Bernoulli Sequences

Poland, Jan; Hutter, Marcus


We consider the Minimum Description Length principle for online sequence prediction. If the underlying model class is discrete, then the total expected square loss is a particularly interesting performance measure: (a) this quantity is bounded, implying convergence with probability one, and (b) it additionally specifies a rate of convergence. Generally, for MDL only exponential loss bounds hold, as opposed to the linear bounds for a Bayes mixture. We show that this is even the case if the model...[Show more]

CollectionsANU Research Publications
Date published: 2004
Type: Conference paper
Source: Algorithmic Learning Theory: 15th International Conference, ALT 2004, Pedova, Italy, October 2004, Proceedings


File Description SizeFormat Image
01_Poland_On_the_Convergence_Speed_of_2004.pdf351.16 kBAdobe PDF    Request a copy

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

Updated:  17 November 2022/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator