The relationship between the Bayesian approach and the minimum description length approach is established. We sharpen and clarify the general modeling principles MDL and MML, abstracted as the ideal MDL principle and defined from Bayes's rule by means of Kolmogorov complexity. The basic condition under which the ideal principle should be applied is encapsulated as the Fundamental Inequality, which in broad terms states that the principle is valid when the data are random, relative to every contemplated hypothesis and also these hypotheses are random relative to the (universal) prior. Basically, the ideal principle states that the prior probability associated with the hypothesis should be given by the algorithmic universal probability, and the sum of the log universal probability of the model plus the log of the probability of the data given the model should be minimized. If we restrict the model class to the finite sets then application of the ideal principle turns into Kolmogorov's mi...

While Kolmogorov complexity is the accepted absolute measure of information content of an individual finite object, a similarly absolute notion is needed for the relation between an individual data sample and an individual model summarizing the information in the data, for example, a finite set (or probability distribution) where the data sample typically came from. The statistical theory based on such relations between individual objects can be called algorithmic statistics, in contrast to classical statistical theory that deals with relations between probabilistic ensembles. We develop the algorithmic theory of statistic, sufficient statistic, and minimal sufficient statistic. This theory is based on two-part codes consisting of the code for the statistic (the model summarizing the regularity, the meaningful information, in the data) and the model-to-data code. In contrast to the situation in probabilistic statistical theory, the algorithmic relation of (minimal) sufficiency is an absolute relation between the individual model and the individual data sample. We distinguish implicit and explicit descriptions of the models. We give characterizations of algorithmic (Kolmogorov) minimal sufficient statistic for all data samples for both description modes in the explicit mode under some constraints. We also strengthen and elaborate earlier results on the "Kolmogorov structure function" and "absolutely non-stochastic objects" those rare objects for which the simplest models that summarize their relevant information (minimal sucient statistics) are at least as complex as the objects themselves. We demonstrate a close relation between the probabilistic notions and the algorithmic ones: (i) in both cases there is an "information non-increase" law; (ii) it is shown that a function is a...

This paper is a survey of concepts and results related to simple Kolmogorov complexity, prefix complexity and resource-bounded complexity. We also consider a new type of complexity--- statistical complexity closely related to mathematical statistics. Unlike other discoverers of algorithmic complexity, A. N. Kolmogorov's leading motive was developing on its basis a mathematical theory more adequately substantiating applications of probability theory, mathematical statistics and information theory. Kolmogorov wanted to deduce properties of a random object from its complexity characteristics without use of the notion of probability. In the first part of this paper we present several results in this direction. Though the subsequent development of algorithmic complexity and randomness was different, algorithmic complexity has successful applications in a traditional probabilistic framework. In the second part of the paper we consider applications to the estimation of parameters and the definition of Bernoulli sequences. All considerations have finite combinatorial character. 1.

Andrei Nikolaevich Kolmogorov was the foremost contributor to the mathematical and philosophical foundations of probability in the twentieth century, and his thinking on the topic is still potent today. In this article we first review the three stages of Kolmogorov's work on the foundations of probability: (1) his formulation of measure-theoretic probability, 1933, (2) his frequentist theory of probability, 1963, and (3) his algorithmic theory of randomness, 1965--1987. We also discuss another approach to the foundations of probability, based on martingales, that Kolmogorov did not consider.

Kolmogorov's goal in proposing his complexity conception of probability was to provide a better foundation for the applications of probability (as opposed to the theory of probability; he believed that his 1933 axioms were sufficient for the theory of probability). The complexity conception was a natural development of Kolmogorov's earlier frequentist conception combined with (a) his conviction that only finite data sequences are of any interest in the applications of probability, and (b) Turing's discovery of the universal computing device. Besides the complexity conception itself, its developments by Martin-Lof, Levin et al will be briefly discussed; I will also list some advantages and limitations of Kolmogorov's complexity conception and the algorithmic theory of randomness in general. Introduction 1 Theory Applications Kolmogorov's axiomatic conception of probability Modern algorithmic theory of randomness Kolmogorov's complexity conception of probability Conditi...

) Peter G'acs ? , John Tromp, and Paul Vit'anyi ?? Abstract. While Kolmogorov complexity is the accepted absolute measure of information content of an individual finite object, a similarly absolute notion is needed for the relation between an individual data sample and an individual model summarizing the information in the data, for example, a finite set where the data sample typically came from. The statistical theory based on such relations between individual objects can be called algorithmic statistics, in contrast to ordinary statistical theory that deals with relations between probabilistic ensembles. We develop a new algorithmic theory of typical statistic, sufficient statistic, and minimal sufficient statistic. 1 Introduction We take statistical theory to ideally consider the following problem: Given a data sample and a family of models (hypotheses) one wants to select the model that produced the data. But a priori it is possible that the data is atypical for the...