Asymptotics of discrete MDL for online prediction

@article{Poland2005AsymptoticsOD,
  title={Asymptotics of discrete MDL for online prediction},
  author={J. Poland and Marcus Hutter},
  journal={IEEE Transactions on Information Theory},
  year={2005},
  volume={51},
  pages={3780-3795}
}
  • J. Poland, Marcus Hutter
  • Published 2005
  • Mathematics, Computer Science
  • IEEE Transactions on Information Theory
  • Minimum description length (MDL) is an important principle for induction and prediction, with strong relations to optimal Bayesian learning. This paper deals with learning processes which are independent and identically distributed (i.i.d.) by means of two-part MDL, where the underlying model class is countable. We consider the online learning framework, i.e., observations come in one by one, and the predictor is allowed to update its state of mind after each time step. We identify two ways of… CONTINUE READING
    32 Citations
    Erratum to "Asymptotics of Discrete MDL for Online Prediction"
    • J. Poland
    • Mathematics, Computer Science
    • IEEE Trans. Inf. Theory
    • 2006
    On the Consistency of Discrete Bayesian Learning
    • J. Poland
    • Mathematics, Computer Science
    • STACS
    • 2007
    Discrete MDL Predicts in Total Variation
    • 12
    • PDF
    Consistency Theorems for Discrete Bayesian Learning
    • PDF
    Consistency of discrete Bayesian learning
    • J. Poland
    • Mathematics, Computer Science
    • Theor. Comput. Sci.
    • 2008
    • 1
    The Missing Consistency Theorem for Bayesian Learning: Stochastic Model Selection
    • J. Poland
    • Mathematics, Computer Science
    • ALT
    • 2006
    • 2
    Potential Functions for Stochastic Model Selection
    • 2
    • PDF

    References

    SHOWING 1-10 OF 64 REFERENCES
    On the Convergence Speed of MDL Predictions for Bernoulli Sequences
    • 18
    • PDF
    Convergence of Discrete MDL for Sequential Prediction
    • 18
    • PDF
    Strong Asymptotic Assertions for Discrete MDL in Regression and Classification
    • 7
    • PDF
    Sequence Prediction Based on Monotone Complexity
    • 18
    • PDF
    How to use expert advice
    • 607
    • PDF
    Minimum description length induction, Bayesianism, and Kolmogorov complexity
    • 251
    • PDF
    Information-theoretic asymptotics of Bayes methods
    • 436
    • PDF
    Probability Theory I
    • 6,168
    • PDF
    A Formal Theory of Inductive Inference. Part II
    • 1,587
    • PDF