On Universal Prediction and Bayesian Confirmation

@article{Hutter2007OnUP,
  title={On Universal Prediction and Bayesian Confirmation},
  author={Marcus Hutter},
  journal={ArXiv},
  year={2007},
  volume={abs/0709.1516}
}
  • Marcus Hutter
  • Published 2007
  • Computer Science, Mathematics
  • ArXiv
  • Abstract The Bayesian framework is a well-studied and successful framework for inductive reasoning, which includes hypothesis testing and confirmation, parameter estimation, sequence prediction, classification, and regression. But standard statistical guidelines for choosing the model class and prior are not always available or can fail, in particular in complex situations. Solomonoff completed the Bayesian framework by providing a rigorous, unique, formal, and universal choice for the model… CONTINUE READING
    80 Citations
    Foundations of Induction
    On the Computability of Conditional Probability
    • 14
    • PDF
    On Finding Predictors for Arbitrary Families of Processes
    • D. Ryabko
    • Mathematics, Computer Science
    • J. Mach. Learn. Res.
    • 2010
    • 12
    • Highly Influenced
    • PDF
    Causal Inference Using the Algorithmic Markov Condition
    • 160
    • PDF
    Characterizing predictable classes of processes
    • D. Ryabko
    • Mathematics, Computer Science
    • UAI
    • 2009
    • 6
    • PDF
    Replacing Causal Faithfulness with Algorithmic Independence of Conditionals
    • 30
    • Highly Influenced
    • PDF
    Noncomputable Conditional Distributions
    • 54
    • PDF
    The Foundations of Solomonoff Prediction
    • 1

    References

    SHOWING 1-10 OF 61 REFERENCES
    On Generalized Computable Universal Priors and their Convergence
    • Marcus Hutter
    • Computer Science, Mathematics
    • Theor. Comput. Sci.
    • 2006
    • 5
    • PDF
    Optimality of Universal Bayesian Sequence Prediction for General Loss and Alphabet
    • Marcus Hutter
    • Mathematics, Computer Science
    • J. Mach. Learn. Res.
    • 2003
    • 36
    • PDF
    On the Existence and Convergence of Computable Universal Priors
    • 14
    • PDF
    The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions
    • 66
    • PDF
    On the Convergence Speed of MDL Predictions for Bernoulli Sequences
    • 18
    • PDF
    MDL convergence speed for Bernoulli sequences
    • 16
    • PDF
    A Formal Theory of Inductive Inference. Part II
    • 1,587
    • Highly Influential
    • PDF
    Information-theoretic asymptotics of Bayes methods
    • 435
    • PDF