Asymptotics of Discrete MDL for Online Prediction

Details Asymptotics of Discrete MDL for Online Prediction Asymptotics of Discrete MDL for Online Prediction

2005-06-08

arxiv.org/abs/cs/0506022v1

IEEE Transactions on Information Theory, 51:11 (2005) 3780-3795

Computer Science

Information Theory

34 pages

Scientific paper

10.1109/TIT.2005.856956

Minimum Description Length (MDL) is an important principle for induction and prediction, with strong relations to optimal Bayesian learning. This paper deals with learning non-i.i.d. processes 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 his 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.

Affiliated with

Also associated with

No associations

Rating

Asymptotics of Discrete MDL for Online Prediction does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Asymptotics of Discrete MDL for Online Prediction, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Asymptotics of Discrete MDL for Online Prediction will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-538495