On Sequence Prediction for Arbitrary Measures

@article{Ryabko2007OnSP,
  title={On Sequence Prediction for Arbitrary Measures},
  author={D. Ryabko and Marcus Hutter},
  journal={2007 IEEE International Symposium on Information Theory},
  year={2007},
  pages={2346-2350}
}
  • D. Ryabko, Marcus Hutter
  • Published 2007
  • Mathematics, Computer Science
  • 2007 IEEE International Symposium on Information Theory
  • Suppose we are given two probability measures on the set of one-way infinite finite-alphabet sequences. Consider the question when one of the measures predicts the other, that is, when conditional probabilities converge (in a certain sense), if one of the measures is chosen to generate the sequence. This question may be considered a refinement of the problem of sequence prediction in its most general formulation: for a given class of probability measures, does there exist a measure which… CONTINUE READING

    Topics from this paper.

    Prediction of maximal aerobic power in man
    7
    Absolutely No Free Lunches!
    • G. Belot
    • Computer Science, Mathematics
    • 2020
    Tractability of batch to sequential conversion
    Nonparametric General Reinforcement Learning
    12
    Offline to Online Conversion
    1
    On the Relation between Realizable and Nonrealizable Cases of the Sequence Prediction Problem
    14

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 14 REFERENCES
    A flagellin-induced complex of the receptor FLS2 and BAK1 initiates plant defence
    1302
    MAP estimation for hyperspectral image resolution enhancement using an auxiliary sensor
    196
    Educational Vouchers and Cream Skimming
    186
    Russian Mathematical Surveys
    • 1970
    Probability
    2706
    On the Foundations of Universal Sequence Prediction
    15