Skip navigation
Skip navigation

On sequence predictions for arbitrary measures

Ryabko, Daniil; Hutter, Marcus


Suppose we are given two probability measures on the set of one-way infinite finite-alphabet sequences. Consider the question when one of the measures predicts the other, that is, when conditional probabilities converge (in a certain sense), if one of the measures is chosen to generate the sequence. This question may be considered a refinement of the problem of sequence prediction in its most general formulation: for a given class of probability measures, does there exist a measure which...[Show more]

CollectionsANU Research Publications
Date published: 2007
Type: Conference paper
Source: Proceedings of IEEE International Symposium on Information Theory (ISIT 2007)
DOI: 10.1109/ISIT.2007.4557570


File Description SizeFormat Image
01_Ryabko_On_sequence_predictions_for_2007.pdf220.45 kBAdobe PDF    Request a copy
02_Ryabko_On_sequence_predictions_for_2007.pdf67.67 kBAdobe PDF    Request a copy
03_Ryabko_On_sequence_predictions_for_2007.pdf297.34 kBAdobe PDF    Request a copy

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

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator