License
When quoting this document, please refer to the following
URN: urn:nbn:de:0030-drops-6331
URL: http://drops.dagstuhl.de/opus/volltexte/2006/633/
Go to the corresponding Portal

Hay, Nick

Error in Enumerable Sequence Prediction

pdf-format:
Document 1.pdf (142 KB)

Abstract

We outline a method for quantifying the error of a sequence prediction. With sequence predictions represented by semimeasures $ u(x)$ we define their error to be $-log_2 u(x)$. We note that enumerable semimeasures are those which model the sequence as the output of a computable system given unknown input. Using this we define the simulation complexity of a computable system $C$ relative to another $U$ giving an emph{exact} bound on their difference in error. This error in turn gives an exact upper bound on the number of predictions $ u$ gets incorrect.

BibTeX - Entry

@InProceedings{hay:DSP:2006:633,
  author =	{Nick Hay},
  title =	{Error in Enumerable Sequence Prediction},
  booktitle =	{Kolmogorov Complexity and Applications},
  year =	{2006},
  editor =	{Marcus Hutter  and Wolfgang Merkle and Paul M.B. Vitanyi},
  number =	{06051},
  series =	{Dagstuhl Seminar Proceedings},
  ISSN =	{1862-4405},
  publisher =	{Internationales Begegnungs- und Forschungszentrum f{\"u}r Informatik (IBFI), Schloss Dagstuhl, Germany},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2006/633},
  annote =	{Keywords: Sequence prediction, Solomonoff induction, enumerable semimeasures}
}

Keywords: Sequence prediction, Solomonoff induction, enumerable semimeasures
Seminar: 06051 - Kolmogorov Complexity and Applications
Issue Date: 2006
Date of publication: 31.07.2006

DROPS-Home | Fulltext Search | Imprint Published by LZI