Abstract
We consider the problem of sequence prediction in a probabilistic setting. Let there be given a class \(\mathcal C\) of stochastic processes (probability measures on the set of one-way infinite sequences). We are interested in the question of what are the conditions on \(\mathcal C\) under which there exists a predictor (also a stochastic process) for which the predicted probabilities converge to the correct ones if any of the processes in \(\mathcal C\) is chosen to generate the data. We find some sufficient conditions on \(\mathcal C\) under which such a predictor exists. Some of the conditions are asymptotic in nature, while others are based on the local (truncated to first observations) behaviour of the processes. The conditions lead to constructions of the predictors. In some cases we obtain rates of convergence that are optimal up to an additive logarithmic term. We emphasize that the framework is completely general: the stochastic processes considered are not required to be i.i.d., stationary, or to belong to some parametric family.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Arimoto, S.: An algorithm for computing the capacity of arbitrary discrete memoryless channels. IEEE Transactions on Information Theory IT-I 8, 14–20 (1972)
Blackwell, D., Dubins, L.: Merging of opinions with increasing information. Annals of Mathematical Statistics 33, 882–887 (1962)
Gallager, R.: Source Coding With Side Information and Universal Coding (unplublished) M.I.T. LIDS-P-937 (1976) (revised 1979)
Haussler, D.: A General Minimax Result for Relative Entropy. IEEE Transactions on Information Theory 43(4), 1276–1280 (1997)
Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin (2005)
Jackson, M., Kalai, E., Smorodinsky, R.: Bayesian representation of stochastic processes under learning: de Finetti revisited. Econometrica 67(4), 794–875 (1999)
Krichevsky, R.: Universal Compression and Retrival. Kluwer Academic Publishers, Dordrecht (1993)
Ryabko, B.: Coding of a source with unknown but ordered probabilities. Problems of Information Transmission 15(2), 134–138 (1979)
Ryabko, B.: Prediction of random sequences and universal coding. Problems of Information Transmission 24, 87–96 (1988)
Ryabko, D.: On sample complexity for computational classification problems. Algorithmica 49(1), 69–77 (2007)
Ryabko, D., Hutter, M.: On sequence prediction for arbitrary measures. In: Proc. 2007 IEEE International Symposium on Information Theory, Nice, France, pp. 2346–2350 (2007)
Ryabko, D., Hutter, M.: Predicting Non-Stationary Processes. Applied Mathematics Letters 21(5), 477–482 (2008)
Shiryaev, A.: Probability. Springer, Heidelberg (1996)
Shtarkov, Yu.: Universal sequential coding of single messages. Problems of Information Transmission 23, 3–17 (1988)
Solomonoff, R.J.: Complexity-based induction systems: comparisons and convergence theorems. IEEE Trans. Information Theory IT-24, 422–432 (1978)
Vapnik, V.: Statistical Learning Theory. John Wiley & Sons, Inc., New York (1998)
Xie, Q., Barron, A.: Asymptotic minimax regret for data compression, gambling, and prediction. IEEE Transactions on Information Theory 46(2), 431–445 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ryabko, D. (2008). Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor. In: Freund, Y., Györfi, L., Turán, G., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2008. Lecture Notes in Computer Science(), vol 5254. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87987-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-87987-9_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87986-2
Online ISBN: 978-3-540-87987-9
eBook Packages: Computer ScienceComputer Science (R0)