Indefinitely Oscillating Martingales

  • Jan Leike
  • Marcus Hutter
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8776)

Abstract

We construct a class of nonnegative martingale processes that oscillate indefinitely with high probability. For these processes, we state a uniform rate of the number of oscillations for a given magnitude and show that this rate is asymptotically close to the theoretical upper bound. These bounds on probability and expectation of the number of upcrossings are compared to classical bounds from the martingale literature. We discuss two applications. First, our results imply that the limit of the minimum description length operator may not exist. Second, we give bounds on how often one can change one’s belief in a given hypothesis when observing a stream of data.

Keywords

Martingales infinite oscillations bounds convergence rates minimum description length mind changes 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Dav13]
    Davis, E.: Bounding changes in probability over time: It is unlikely that you will change your mind very much very often. Technical report (2013), https://cs.nyu.edu/davise/papers/dither.pdf
  2. [Doo53]
    Doob, J.L.: Stochastic Processes. Wiley, New York (1953)MATHGoogle Scholar
  3. [Dur10]
    Durrett, R.: Probability: Theory and Examples, 4th edn. Cambridge University Press (2010)Google Scholar
  4. [Grü07]
    Grünwald, P.D.: The Minimum Description Length Principle. The MIT Press, Cambridge (2007)Google Scholar
  5. [Hut09]
    Hutter, M.: Discrete MDL predicts in total variation. In: Advances in Neural Information Processing Systems 22 (NIPS 2009), pp. 817–825. Curran Associates, Cambridge (2009)Google Scholar
  6. [LH14]
    Leike, J., Hutter, M.: Indefinitely oscillating martingales. Technical report, The Australian National University (2014), http://www.hutter1.net/publ/martoscx.pdf
  7. [LS05]
    Luo, W., Schulte, O.: Mind change efficient learning. In: Auer, P., Meir, R. (eds.) COLT 2005. LNCS (LNAI), vol. 3559, pp. 398–412. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  8. [PH05]
    Poland, J., Hutter, M.: Asymptotics of discrete MDL for online prediction. IEEE Transactions on Information Theory 51(11), 3780–3795 (2005)MathSciNetCrossRefMATHGoogle Scholar
  9. [Ris78]
    Rissanen, J.: Modeling by shortest data description. Automatica 14(5), 465–471 (1978)CrossRefMATHGoogle Scholar
  10. [Wal05]
    Wallace, C.S.: Statistical and Inductive Inference by Minimum Message Length. Springer, Berlin (2005)MATHGoogle Scholar
  11. [WB68]
    Wallace, C.S., Boulton, D.M.: An information measure for classification. Computer Journal 11(2), 185–194 (1968)CrossRefMATHGoogle Scholar
  12. [Xu12]
    Xu, W.: Martingale convergence theorems. Technical report (2012), http://people.maths.ox.ac.uk/xu/Martingale_convergence.pdf

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Jan Leike
    • 1
  • Marcus Hutter
    • 1
  1. 1.The Australian National UniversityAustralia

Personalised recommendations