Computer Science – Computational Complexity
Scientific paper
2002-04-16
Computer Science
Computational Complexity
25 pages LaTeX, 5 figures. In part in Proc 47th IEEE FOCS; this final version (more explanations, cosmetic modifications) to a
Scientific paper
In 1974 Kolmogorov proposed a non-probabilistic approach to statistics and model selection. Let data be finite binary strings and models be finite sets of binary strings. Consider model classes consisting of models of given maximal (Kolmogorov) complexity. The ``structure function'' of the given data expresses the relation between the complexity level constraint on a model class and the least log-cardinality of a model in the class containing the data. We show that the structure function determines all stochastic properties of the data: for every constrained model class it determines the individual best-fitting model in the class irrespective of whether the ``true'' model is in the model class considered or not. In this setting, this happens {\em with certainty}, rather than with high probability as is in the classical case. We precisely quantify the goodness-of-fit of an individual model with respect to individual data. We show that--within the obvious constraints--every graph is realized by the structure function of some data. We determine the (un)computability properties of the various functions contemplated and of the ``algorithmic minimal sufficient statistic.''
Vereshchagin Nikolai
Vitanyi Paul
No associations
LandOfFree
Kolmogorov's Structure Functions and Model Selection does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Kolmogorov's Structure Functions and Model Selection, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Kolmogorov's Structure Functions and Model Selection will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-11113