Practical use of MDL is full of pitfalls in which the practitioners tend to fall head over heels. We analyse the power and the perils in the use of MDL. Generally, the classical approach is inadequate to express the goodness-of-fit of individual models for individual data sets. In practice however, this is precisely what we are interested in: both to express the goodness of a procedure and where and how it can fail. To achieve this practical goal, we paradoxically have to use the, supposedly impractical, vehicle of Kolmogorov complexity.
Pieter W. Adriaans, Paul M. B. Vitányi