previous home search |
LaTeX -
PostScript -
PDF -
Html/Gif
| contact up next |

## On the Convergence Speed of MDL Predictions for Bernoulli Sequences

Authors:Jan Poland and Marcus Hutter (2004) Comments:16 pages Subj-class:Probability Theory; Learning; Artificial Intelligence; Information Theory; Complexity Reference:Proceedings of the 15th International Conference on Algorithmic Learning Theory (ALT 2004) pages 294-308 Report-no:IDSIA-13-04 and cs.LG/0407039 Paper:LaTeX - PostScript - PDF - Html/Gif Slides:PowerPoint (needs tex4ppt) - PDF

Keywords:MDL, Minimum Description Length, Convergence Rate, Prediction, Bernoulli, Discrete Model Class.

Abstract:We consider the Minimum Description Length principle for online sequence prediction. If the underlying model class is discrete, then the total expected square loss is a particularly interesting performance measure: (a) this quantity is bounded, implying convergence with probability one, and (b) it additionally specifies a `rate of convergence'. Generally, for MDL only exponential loss bounds hold, as opposed to the linear bounds for a Bayes mixture. We show that this is even the case if the model class contains only Bernoulli distributions. We derive a new upper bound on the prediction error for countable Bernoulli classes. This implies a small bound (comparable to the one for Bayes mixtures) for certain important model classes. The results apply to many Machine Learning tasks including classification and hypothesis testing. We provide arguments that our theorems generalize to countable classes of i.i.d. models.

previous home search |
LaTeX -
PostScript -
PDF -
Html/Gif
| contact up next |

@InProceedings{Hutter:04mdlspeed, author = "J. Poland and M. Hutter", title = "On the convergence speed of {MDL} predictions for {B}ernoulli sequences", booktitle = "Proc. 15th International Conf. on Algorithmic Learning Theory ({ALT-2004})", address = "Padova", series = "LNAI", volume = "3244", editor = "S. Ben-David and J. Case and A. Maruoka", publisher = "Springer, Berlin", pages = "294--308", year = "2004", url = "http://www.hutter1.net/ai/mdlspeed.htm", http = "http://arxiv.org/abs/cs.LG/0407039", ftp = "ftp://ftp.idsia.ch/pub/techrep/IDSIA-13-04.pdf", keywords = "MDL, Minimum Description Length, Convergence Rate, Prediction, Bernoulli, Discrete Model Class.", abstract = "We consider the Minimum Description Length principle for online sequence prediction. If the underlying model class is discrete, then the total expected square loss is a particularly interesting performance measure: (a) this quantity is bounded, implying convergence with probability one, and (b) it additionally specifies a `rate of convergence'. Generally, for MDL only exponential loss bounds hold, as opposed to the linear bounds for a Bayes mixture. We show that this is even the case if the model class contains only Bernoulli distributions. We derive a new upper bound on the prediction error for countable Bernoulli classes. This implies a small bound (comparable to the one for Bayes mixtures) for certain important model classes. The results apply to many Machine Learning tasks including classification and hypothesis testing. We provide arguments that our theorems generalize to countable classes of i.i.d. models.", }

previous home search |
LaTeX -
PostScript -
PDF -
Html/Gif
| contact up next |