3 search results - page 1 / 1 » Convergence of Discrete MDL for Sequential Prediction |
COLT
2004
Springer
13 years 10 months ago
2004
Springer
We study the properties of the Minimum Description Length principle for sequence prediction, considering a two-part MDL estimator which is chosen from a countable class of models....
CORR
2006
Springer
13 years 4 months ago
2006
Springer
The Minimum Description Length principle for online sequence estimation/prediction in a proper learning setup is studied. If the underlying model class is discrete, then the total...
JCSS
2006
13 years 4 months ago
2006
This paper studies sequence prediction based on the monotone Kolmogorov complexity Km=-log m, i.e. based on universal deterministic/one-part MDL. m is extremely close to Solomonof...