Skip navigation
Skip navigation

Concentration and confidence for discrete Bayesian sequence predictors

Lattimore, Tor; Hutter, Marcus; Sunehag, Peter

Description

Bayesian sequence prediction is a simple technique for predicting future symbols sampled from an unknown measure on infinite sequences over a countable alphabet. While strong bounds on the expected cumulative error are known, there are only limited results on the distribution of this error. We prove tight high-probability bounds on the cumulative error, which is measured in terms of the Kullback-Leibler (KL) divergence. We also consider the problem of constructing upper confidence bounds on the...[Show more]

CollectionsANU Research Publications
Date published: 2013-10-06
Type: Conference paper
URI: http://hdl.handle.net/1885/14715
DOI: 10.1007/978-3-642-40935-6_23

Download

File Description SizeFormat Image
Lattimore et al Concentration and Confidence 2013.pdf217.33 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