Recent Results in Universal and Non-Universal Induction

Author Jan Poland



PDF
Thumbnail PDF

File

DagSemProc.06051.12.pdf
  • Filesize: 219 kB
  • 11 pages

Document Identifiers

Author Details

Jan Poland

Cite AsGet BibTex

Jan Poland. Recent Results in Universal and Non-Universal Induction. In Kolmogorov Complexity and Applications. Dagstuhl Seminar Proceedings, Volume 6051, pp. 1-11, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2006)
https://doi.org/10.4230/DagSemProc.06051.12

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.
Keywords
  • Bayesian learning
  • MDL
  • stochastic model selection
  • prediction with expert advice
  • universal learning
  • Solomonoff induction

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail