Poland, Jan; Hutter, Marcus
We study the properties of the MDL (or maximum penalized
complexity) estimator for Regression and Classification, where the
underlying model class is countable. We show in particular a
finite bound on the Hellinger losses under the only assumption
that there is a ``true'' model contained in the class. This implies
almost sure convergence of the predictive distribution to the true
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.