Kolmogorov's Structure Functions and Model Selection
IEEE Transactions on Information Theory
In 1974, Kolmogorov proposed a nonprobabilistic 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
... s 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 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." Index Terms-Computability, constrained best fit model selection, constrained maximum likelihood (ML), constrained minimum description length (MDL), function prediction, Kolmogorov complexity, Kolmogorov structure function, lossy compression, minimal sufficient statistic, nonprobabilistic statistics, sufficient statistic.