Asymptotics of discrete (MDL) for online prediction

Date

2005

Authors

Poland, Jan
Hutter, Marcus

Journal Title

Journal ISSN

Volume Title

Publisher

Institute of Electrical and Electronics Engineers (IEEE Inc)

Abstract

Minimum description length (MDL) is an important principle for induction and prediction, with strong relations to optimal Bayesian learning. This paper deals with learning processes which are independent and identically distributed (i.i.d.) by means of two-part MDL, where the underlying model class is countable. We consider the online learning framework, i.e., observations come in one by one, and the predictor is allowed to update its state of mind after each time step. We identify two ways of predicting by MDL for this setup, namely, a static and a dynamic one. (A third variant, hybrid MDL, will turn out inferior.) We will prove that under the only assumption that the data is generated by a distribution contained in the model class, the MDL predictions converge to the true values almost surely. This is accomplished by proving finite bounds on the quadratic, the Hellinger, and the Kullback-Leibler loss of the MDL learner, which are, however, exponentially worse than for Bayesian prediction. We demonstrate that these bounds are sharp, even for model classes containing only Bernoulli distributions. We show how these bounds imply regret bounds for arbitrary loss functions. Our results apply to a wide range of setups, namely, sequence prediction, pattern classification, regression, and universal induction in the sense of algorithmic information theory among others.

Description

Keywords

Keywords: Learning systems; Mathematical models; Pattern recognition; Probability distributions; Regression analysis; Theorem proving; Algorithmic information theory; Classification consistency; Discrete model class; Minimum description length (MDL); Sequence predi Algorithmic information theory; Classification; Consistency; Discrete model class; Loss bounds; Minimum description length (MDL); Regression; Sequence prediction; Stabilization; Universal induction

Citation

Source

IEEE Transactions on Information Theory

Type

Journal article

Book Title

Entity type

Access Statement

License Rights

Restricted until