Strong asymptotic assertions for discrete MDL in regression and classification
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 ...[Show more]
|Collections||ANU Research Publications|
|Poland and Hutter Strong Asymptotic Assertions 2005.pdf||175.8 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.