Computer Science – Learning
Scientific paper
1999-01-27
IEEE Transactions on Information Theory, 46:2(2000), 446-464
Computer Science
Learning
35 pages, Latex. Submitted IEEE Trans. Inform. Theory
Scientific paper
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 minimal sufficient statistic. In general we show that data compression is almost always the best strategy, both in hypothesis identification and prediction.
Li Ming
Vitanyi Paul
No associations
LandOfFree
Minimum Description Length Induction, Bayesianism, and Kolmogorov Complexity 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 Minimum Description Length Induction, Bayesianism, and Kolmogorov Complexity, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Minimum Description Length Induction, Bayesianism, and Kolmogorov Complexity will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-251499