A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit the original URL.
The file type is `application/pdf`

.

##
###
Kolmogorov's Structure Functions and Model Selection

2004
*
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

doi:10.1109/tit.2004.838346
fatcat:gurvcw7pivbwzgbp4clynqbu5i