Abstract
This paper accomplishes the last step in a series of consistency theorems for Bayesian learners based on discree hypothesis class, being initiated by Solomonoff’s 1978 work. Precisely, we show the generalization of a performance guarantee for Bayesian stochastic model selection, which has been proven very recently by the author for finite observation space, to countable and continuous observation space as well as mixtures. This strong result is (to the author’s knowledge) the first of this kind for stochastic model selection. It states almost sure consistency of the learner in the realizable case, that is, where one of the hypotheses/models considered coincides with the truth. Moreover, it implies error bounds on the difference of the predictive distribution to the true one, and even loss bounds w.r.t. arbitrary loss functions. The set of consistency theorems for the three natural variants of discrete Bayesian prediction, namely marginalization, MAP, and stochastic model selection, is thus being completed for general observation space. Hence, this is the right time to recapitulate all these results, to present them in a unified context, and to discuss the different situations of Bayesian learning and its different methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Poland, J.: The missing consistency theorem for Bayesian learning: Stochastic model selection. In: Balcázar, J.L., Long, P.M., Stephan, F. (eds.) ALT 2006. LNCS (LNAI), vol. 4264, pp. 259–273. Springer, Heidelberg (2006)
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)
Barron, A.R., Rissanen, J.J., Yu, B.: The minimum description length principle in coding and modeling. IEEE Trans. Inform. Theory 44, 2743–2760 (1998)
Wallace, C.S., Boulton, D.M.: An information measure for classification. Computer Journal 11, 185–194 (1968)
Wallace, C.S., Dowe, D.L.: Minimum Message Length and Kolmogorov Complexity. Computer Journal 42, 270–283 (1999)
Rissanen, J.J.: Fisher Information and Stochastic Complexity. IEEE Trans. Inform. Theory 42, 40–47 (1996)
Barron, A.R., Cover, T.M.: Minimum complexity density estimation. IEEE Trans. Inform. Theory 37, 1034–1054 (1991)
Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin (2004)
Poland, J., Hutter, M.: Asymptotics of discrete MDL for online prediction. IEEE Transactions on Information Theory 51, 3780–3795 (2005)
Grünwald, P., Langford, J.: Suboptimal behaviour of Bayes and MDL in classification under misspecification. In: Shawe-Taylor, J., Singer, Y. (eds.) COLT 2004. LNCS (LNAI), vol. 3120, pp. 331–347. Springer, Heidelberg (2004)
Comley, J.W., Dowe, D.L.: Minimum message length and generalized Bayesian nets with asymmetric languages. In: Grünwald, P., Myung, I.J., Pitt, M.A. (eds.) Advances in Minimum Description Length: Theory and Applications, pp. 265–294 (2005)
Solomonoff, R.J.: Complexity-based induction systems: comparisons and convergence theorems. IEEE Trans. Inform. Theory 24, 422–432 (1978)
Poland, J., Hutter, M.: MDL convergence speed for Bernoulli sequences. Statistics and Computing 16, 161–175 (2006)
Borovkov, A.A., Moullagaliev, A.: Mathematical Statistics. Gordon & Breach, Newark (1998)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Poland, J. (2007). On the Consistency of Discrete Bayesian Learning. In: Thomas, W., Weil, P. (eds) STACS 2007. STACS 2007. Lecture Notes in Computer Science, vol 4393. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70918-3_35
Download citation
DOI: https://doi.org/10.1007/978-3-540-70918-3_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-70917-6
Online ISBN: 978-3-540-70918-3
eBook Packages: Computer ScienceComputer Science (R0)