Universal Modeling: Introduction to modern MDL
We give a tutorial introduction to the *modern* Minimum Description Length (MDL) Principle, taking into account the many refinements and developments that have taken place in the 1990s. These do not seem to be widely known outside the information theory community. We will especially emphasize the use of MDL in classification. We also consider the connections between MDL, Bayesian inference, maximum entropy inference and structural risk minimization.
Author: Peter Grünwald, National Research Institute For Mathematics And Computer Science