Universal Prediction of Selected Bits

  • Tor Lattimore
  • Marcus Hutter
  • Vaibhav Gavane
Conference paper

DOI: 10.1007/978-3-642-24412-4_22

Part of the Lecture Notes in Computer Science book series (LNCS, volume 6925)
Cite this paper as:
Lattimore T., Hutter M., Gavane V. (2011) Universal Prediction of Selected Bits. In: Kivinen J., Szepesvári C., Ukkonen E., Zeugmann T. (eds) Algorithmic Learning Theory. ALT 2011. Lecture Notes in Computer Science, vol 6925. Springer, Berlin, Heidelberg

Abstract

Many learning tasks can be viewed as sequence prediction problems. For example, online classification can be converted to sequence prediction with the sequence being pairs of input/target data and where the goal is to correctly predict the target data given input data and previous input/target pairs. Solomonoff induction is known to solve the general sequence prediction problem, but only if the entire sequence is sampled from a computable distribution. In the case of classification and discriminative learning though, only the targets need be structured (given the inputs). We show that the normalised version of Solomonoff induction can still be used in this case, and more generally that it can detect any recursive sub-pattern (regularity) within an otherwise completely unstructured sequence. It is also shown that the unnormalised version can fail to predict very simple recursive sub-patterns.

Keywords

Sequence prediction Solomonoff induction online classification discriminative learning algorithmic information theory 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Tor Lattimore
    • 1
  • Marcus Hutter
    • 2
  • Vaibhav Gavane
    • 3
  1. 1.Australian National UniversityAustralia
  2. 2.Australian National University and ETH ZürichAustralia
  3. 3.VIT UniversityVelloreIndia

Personalised recommendations