53 Downloads (Pure)

Abstract

We construct universal prediction systems in the spirit of Popper's falsifiability and Kolmogorov complexity and randomness. These prediction systems do not depend on any statistical assumptions (but under the IID assumption they dominate, to within the usual accuracy, conformal prediction). Our constructions give rise to a theory of algorithmic complexity and randomness of time containing analogues of several notions and results of the classical theory of Kolmogorov complexity and randomness.
Original languageEnglish
Pages (from-to)1-24
Number of pages24
JournalAnnals of Mathematics and Artificial Intelligence
Volume81
Issue number1-2
Early online date19 Apr 2017
DOIs
Publication statusPublished - Oct 2017

Keywords

  • Conformal prediction
  • Prediction systems
  • Probability-free learning
  • Universal prediction

Cite this