Universal Probability-Free Conformal Prediction

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9653)

Abstract

We construct a universal prediction system in the spirit of Popper’s falsifiability and Kolmogorov complexity. This prediction system does not depend on any statistical assumptions, but under the IID assumption it dominates, although in a rather weak sense, conformal prediction.

Keywords

Conformal prediction Prediction systems Probability-free Universal prediction 

References

  1. 1.
    Popper, K.R.: Logik der Forschung. Springer, Vienna (1934), English translation: The Logic of Scientific Discovery. Hutchinson, London (1959)Google Scholar
  2. 2.
    Popper, K.R.: Objective Knowledge: An Evolutionary Approach, revised edn. Clarendon Press, Oxford (1979). first edition: 1972Google Scholar
  3. 3.
    Popper, K.R.: All Life is Problem Solving. Routledge, Abingdon (1999)Google Scholar
  4. 4.
    Rissanen, J.: A universal prior for integers and estimation by minimum description length. Ann. Stat. 11, 416–431 (1983)MathSciNetCrossRefMATHGoogle Scholar
  5. 5.
    Shen, A.: Around Kolmogorov complexity: basic notions and results. In: Vovk, V., Papadopoulos, H., Gammerman, A. (eds.) Measures of Complexity: Festschrift for Alexey Chervonenkis, pp. 75–115. Springer, Cham (2015)CrossRefGoogle Scholar
  6. 6.
    Vovk, V.: The basic conformal prediction framework. In: Balasubramanian, V.N., Ho, S.S., Vovk, V. (eds.) Conformal Prediction for Reliable Machine Learning: Theory, Adaptations, and Applications, chap. 1, pp. 3–19. Elsevier, Amsterdam (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Royal Holloway, University of LondonEghamUK
  2. 2.University of HawaiiHonoluluUSA

Personalised recommendations