Abstract
Bayes’ rule specifies how to obtain a posterior from a class of hypotheses endowed with a prior and the observed data. There are three principle ways to use this posterior for predicting the future: marginalization (integration over the hypotheses w.r.t. the posterior), MAP (taking the a posteriori most probable hypothesis), and stochastic model selection (selecting a hypothesis at random according to the posterior distribution). If the hypothesis class is countable and contains the data generating distribution, strong consistency theorems are known for the former two methods, asserting almost sure convergence of the predictions to the truth as well as loss bounds. We prove the first corresponding results for stochastic model selection. As a main technical tool, we will use the concept of a potential: this quantity, which is always positive, measures the total possible amount of future prediction errors. Precisely, in each time step, the expected potential decrease upper bounds the expected error. We introduce the entropy potential of a hypothesis class as its worst-case entropy with regard to the true distribution. We formulate our results in the online classification framework, but they are equally applicable to the prediction of non-i.i.d. sequences.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Freund, Y., Seung, H.S., Shamir, E., Tishby, N.: Selective sampling using the query by committee algorithm. Machine Learning 28, 133 (1997)
McAllester, D.: PAC-bayesian stochastic model selection. Machine Learning 51, 5–21 (2003)
Blackwell, D., Dubins, L.: Merging of opinions with increasing information. Annals of Mathematical Statistics 33, 882–887 (1962)
Clarke, B.S., Barron, A.R.: Information-theoretic asymptotics of Bayes methods. IEEE Trans. Inform. Theory 36, 453–471 (1990)
Rissanen, J.J.: Fisher Information and Stochastic Complexity. IEEE Trans. Inform. Theory 42, 40–47 (1996)
Solomonoff, R.J.: Complexity-based induction systems: comparisons and convergence theorems. IEEE Trans. Inform. Theory 24, 422–432 (1978)
Poland, J., Hutter, M.: Convergence of discrete MDL for sequential prediction. In: Shawe-Taylor, J., Singer, Y. (eds.) COLT 2004. LNCS (LNAI), vol. 3120, pp. 300–314. Springer, Heidelberg (2004)
Poland, J., Hutter, M.: Asymptotics of discrete MDL for online prediction. IEEE Transactions on Information Theory 51, 3780–3795 (2005)
Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin (2004)
Poland, J., Hutter, M.: On the convergence speed of MDL predictions for bernoulli sequences. In: Ben-David, S., Case, J., Maruoka, A. (eds.) ALT 2004. LNCS (LNAI), vol. 3244, pp. 294–308. Springer, Heidelberg (2004)
Hutter, M.: Convergence and loss bounds for Bayesian sequence prediction. IEEE Trans. Inform. Theory 49, 2061–2067 (2003)
Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. In: 30th Annual Symposium on Foundations of Computer Science, Research Triangle Park, North Carolina, pp. 256–261. IEEE, Los Alamitos (1989)
Vovk, V.G.: Aggregating strategies. In: Proc. Third Annual Workshop on Computational Learning Theory, Rochester, pp. 371–383. ACM Press, New York (1990)
Hutter, M., Poland, J.: Adaptive online prediction by following the perturbed leader. Journal of Machine Learning Research 6, 639–660 (2005)
Cesa-Bianchi, N., Lugosi, G.: Potential-based algorithms in on-line prediction and game theory. Machine Learning 51, 239–261 (2003)
Li, M., Vitányi, P.M.B.: An introduction to Kolmogorov complexity and its applications, 2nd edn. Springer, Heidelberg (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Poland, J. (2006). The Missing Consistency Theorem for Bayesian Learning: Stochastic Model Selection. In: Balcázar, J.L., Long, P.M., Stephan, F. (eds) Algorithmic Learning Theory. ALT 2006. Lecture Notes in Computer Science(), vol 4264. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11894841_22
Download citation
DOI: https://doi.org/10.1007/11894841_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-46649-9
Online ISBN: 978-3-540-46650-5
eBook Packages: Computer ScienceComputer Science (R0)