Abstract
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 expected square loss is a particularly interesting performance measure: (a) this quantity is finitely bounded, implying convergence with probability one, and (b) it additionally specifies the convergence speed. For MDL, in general one can only have loss bounds which are finite but exponentially larger than those for Bayes mixtures. 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. We discuss the application to Machine Learning tasks such as classification and hypothesis testing, and generalization to countable classes of i.i.d. models.
Similar content being viewed by others
References
Barron A. R. and Cover T. M. 1991. Minimum complexity density estimation. IEEE Trans. on Information Theory 37(4): 1034–1054.
Barron A. R., Rissanen J. J., and Yu B. 1998. The minimum description length principle in coding and modeling. IEEE Trans. on Information Theory 44(6): 2743–2760.
Clarke B. S. and Barron A.R. 1990. Information-theoretic asymptotics of Bayes methods. IEEE Trans. on Information Theory 36: 453–471.
Gács P. 1983. On the relation between descriptional complexity and algorithmic probability. Theoretical Computer Science 22: 71–93.
Grünwald P. and Langford J. 2004. Suboptimal behaviour of Bayes and MDL in classification under misspecification. In 17th Annual Conference on Learning Theory (COLT, pp. 331–347.
Hutter M. 2001. Convergence and error bounds for universal prediction of nonbinary sequences. Proc. 12th Eurpean Conference on Machine Learning (ECML-2001), pp. 239–250
Hutter M. 2003a. Convergence and loss bounds for Bayesian sequence prediction. IEEE Trans. on Information Theory 49(8): 2061–2067.
Hutter M. 2003b. Optimality of universal Bayesian prediction for general loss and alphabet. Journal of Machine Learning Research 4: 971–1000.
Hutter. M. 2003c. Sequence prediction based on monotone complexity. In Proc. 16th Annual Conference on Learning Theory (COLT-2003), Lecture Notes in Artificial Intelligence, Berlin, Springer, pp. 506–521.
Hutter M. 2005. Sequential predictions based on algorithmic complexity. Journal of Computer and System Sciences 72(1): 95–117.
Levin L. A. 1973. On the notion of a random sequence. Soviet Math. Dokl. 14(5): 1413–1416.
Li J. Q. 1999. Estimation of Mixture Models. PhD thesis, Dept. of Statistics. Yale University.
Li M. and Vit’anyi P. M. B. 1997. An introduction to Kolmogorov complexity and its applications. Springer, 2nd edition.
Poland J. and Hutter M. 2004a. Convergence of discrete MDL for sequential prediction. In 17th Annual Conference on Learning Theory (COLT), pp. 300–314.
Poland J. and Hutter M. 2004b. On the convergence speed of MDL predictions for Bernoulli sequences. In International Conference on Algorithmic Learning Theory (ALT), pp. 294– 308.
Poland J. and Hutter M. 2005. Strong asymptotic assertions for discrete MDL in regression and classification. In Benelearn 2005 (Ann. Machine Learning Conf. of Belgium and the Netherlands)
Rissanen J. J. 1996. Fisher Information and Stochastic Complexity. IEEE Trans. on Information Theory 42(1): 40– 47.
Rissanen J. J. 1999. Hypothesis selection and testing by the MDL principle. The Computer Journal 42(4): 260–269.
Solomonoff R. J. 1978. Complexity-based induction systems: comparisons and convergence theorems. IEEE Trans. Information Theory IT-24: 422–432.
Vitányi P. M. and Li M. 2000. Minimum description length induction, Bayesianism, and Kolmogorov complexity. IEEE Trans. on Information Theory 46(2): 446–464.
Vovk V. G. 1997. Learning about the parameter of the Bernoulli model. Journal of Computer and System Sciences 55: 96–104.
Zhang T. 2004. On the convergence of MDL density estimation. In Proc. 17th Annual Conference on Learning Theory (COLT), pp. 315–330,
Zvonkin A. K. and Levin L. A. 1970. The complexity of finite objects and the development of the concepts of information and randomness by means of the theory of algorithms. Russian Mathematical Surveys 25(6): 83–124.
Author information
Authors and Affiliations
Corresponding author
Additional information
A shorter version of this paper (Poland and Hutter, 2004b) appeared in ALT 2004.
This work was supported by SNF grant 2100-67712.02
This research was done while the first author was with IDSIA, Switzerland.
Rights and permissions
About this article
Cite this article
Poland, J., Hutter, M. MDL convergence speed for Bernoulli sequences. Stat Comput 16, 161–175 (2006). https://doi.org/10.1007/s11222-006-6746-3
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s11222-006-6746-3