License
When quoting this document, please refer to the following
URN: urn:nbn:de:0030-drops-6355
URL: http://drops.dagstuhl.de/opus/volltexte/2006/635/
Go to the corresponding Portal


Poland, Jan

Recent Results in Universal and Non-Universal Induction

pdf-format:
Document 1.pdf (219 KB)


Abstract

We present and relate recent results in prediction based on countable classes of either probability (semi-)distributions or base predictors. Learning by Bayes, MDL, and stochastic model selection will be considered as instances of the first category. In particular, we will show how analog assertions to Solomonoff's universal induction result can be obtained for MDL and stochastic model selection. The second category is based on prediction with expert advice. We will present a recent construction to define a universal learner in this framework.

BibTeX - Entry

@InProceedings{poland:DSP:2006:635,
  author =	{Jan Poland},
  title =	{Recent Results in Universal and Non-Universal Induction},
  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/2006/635},
  annote =	{Keywords: Bayesian learning, MDL, stochastic model selection, prediction with expert advice, universal learning, Solomonoff induction}
}

Keywords: Bayesian learning, MDL, stochastic model selection, prediction with expert advice, universal learning, Solomonoff induction
Seminar: 06051 - Kolmogorov Complexity and Applications
Issue Date: 2006
Date of publication: 31.07.2006


DROPS-Home | Fulltext Search | Imprint Published by LZI