License
When quoting this document, please refer to the following
URN: urn:nbn:de:0030-drops-7900
URL: http://drops.dagstuhl.de/opus/volltexte/2006/790/
Go to the corresponding Portal

Ryabko, Daniil ; Hutter, Marcus

Sequence prediction for non-stationary processes

pdf-format:
Document 1.pdf (213 KB)

Abstract

We address the problem of sequence prediction for nonstationary stochastic processes. In particular, given two measures on the set of one-way infinite sequences over a finite alphabet, consider the question whether one of the measures predicts the other. We find some conditions on local absolute continuity under which prediction is possible.

BibTeX - Entry

@InProceedings{ryabko_et_al:DSP:2006:790,
  author =	{Daniil Ryabko and Marcus Hutter},
  title =	{Sequence prediction for non-stationary processes},
  booktitle =	{Combinatorial and Algorithmic Foundations of Pattern and Association Discovery},
  year =	{2006},
  editor =	{Rudolf Ahlswede and Alberto Apostolico and Vladimir I. Levenshtein},
  number =	{06201},
  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/2006/790},
  annote =	{Keywords: Sequence prediction, probability forecasting,  local absolute continuity}
}

Keywords: Sequence prediction, probability forecasting, local absolute continuity
Seminar: 06201 - Combinatorial and Algorithmic Foundations of Pattern and Association Discovery
Issue Date: 2006
Date of publication: 07.11.2006

DROPS-Home | Fulltext Search | Imprint Published by LZI