Skip navigation
Skip navigation

Convergence and loss bounds for Bayesian sequence prediction

Hutter, Marcus


The probability of observing xt at time t, given past observations x1 ⋯ xt-1 can be computed if the true generating distribution μ of the sequences x1x2x3 ⋯ is known. If μ is unknown, but known to belong to a class M one can base one's prediction on

CollectionsANU Research Publications
Date published: 2003
Type: Journal article
Source: IEEE Transactions on Information Theory
DOI: 10.1109/TIT.2003.814488


File Description SizeFormat Image
01_Hutter_Convergence_and_loss_bounds_2003.pdf232.05 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