Skip navigation
Skip navigation

Sequence Prediction based on Monotone Complexity

Hutter, Marcus

Description

This paper studies sequence prediction based on the monotone Kolmogorov complexity Km = -log m, i.e. based on universal deterministic/one-part MDL. m is extremely close to Solomonoff's prior M, the latter being an excellent predictor in deterministic as well as probabilistic environments, where performance is measured in terms of convergence of posteriors or losses. Despite this closeness to M, it is difficult to assess the prediction quality of m, since little is known about the closeness of...[Show more]

CollectionsANU Research Publications
Date published: 2003
Type: Conference paper
URI: http://hdl.handle.net/1885/30261
Source: Computational Learning Theory and Kernel Machines, 16th Annual Conference on Computational Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003, Washington DC, USA, August 24-27, 2003

Download

File Description SizeFormat Image
01_Hutter_Sequence_Prediction_based_on_2003.pdf1.1 MBAdobe PDF    Request a copy


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