Indefinitely Oscillating Martingales
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.
KeywordsMartingales infinite oscillations bounds convergence rates minimum description length mind changes
Unable to display preview. Download preview PDF.
- [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
- [Dur10]Durrett, R.: Probability: Theory and Examples, 4th edn. Cambridge University Press (2010)Google Scholar
- [Grü07]Grünwald, P.D.: The Minimum Description Length Principle. The MIT Press, Cambridge (2007)Google Scholar
- [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
- [LH14]Leike, J., Hutter, M.: Indefinitely oscillating martingales. Technical report, The Australian National University (2014), http://www.hutter1.net/publ/martoscx.pdf
- [Xu12]Xu, W.: Martingale convergence theorems. Technical report (2012), http://people.maths.ox.ac.uk/xu/Martingale_convergence.pdf