Abstract
Many learning tasks can be viewed as sequence prediction problems. For example, online classification can be converted to sequence prediction with the sequence being pairs of input/target data and where the goal is to correctly predict the target data given input data and previous input/target pairs. Solomonoff induction is known to solve the general sequence prediction problem, but only if the entire sequence is sampled from a computable distribution. In the case of classification and discriminative learning though, only the targets need be structured (given the inputs). We show that the normalised version of Solomonoff induction can still be used in this case, and more generally that it can detect any recursive sub-pattern (regularity) within an otherwise completely unstructured sequence. It is also shown that the unnormalised version can fail to predict very simple recursive sub-patterns.
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
Gács, P.: On the relation between descriptional complexity and algorithmic probability. Theoretical Computer Science 22(1-2), 71–93 (1983)
Gács, P.: Expanded and improved proof of the relation between description complexity and algorithmic probability (2008) (unpublished)
Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin (2004)
Hutter, M.: On universal prediction and Bayesian confirmation. Theoretical Computer Science 384(1), 33–48 (2007)
Hutter, M.: Open problems in universal induction & intelligence. Algorithms 3(2), 879–906 (2009)
Hutter, M., Muchnik, A.A.: On semimeasures predicting Martin-Löf random sequences. Theoretical Computer Science 382(3), 247–261 (2007)
Lempp, S., Miller, J., Ng, S., Turetsky, D.: Complexity inequality. Unpublished, private communication (2010)
Li, M., Vitanyi, P.: An Introduction to Kolmogorov Complexity and Its Applications, 3rd edn. Springer, Heidelberg (2008)
Long, P., Servedio, R.: Discriminative Learning Can Succeed Where Generative Learning Fails. In: Lugosi, G., Simon, H.U. (eds.) COLT 2006. LNCS (LNAI), vol. 4005, pp. 319–334. Springer, Heidelberg (2006)
Solomonoff, R.: A formal theory of inductive inference, Part I. Information and Control 7(1), 1–22 (1964)
Solomonoff, R.: A formal theory of inductive inference, Part II. Information and Control 7(2), 224–254 (1964)
Zvonkin, A.K., Levin, L.A.: 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 (1970)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lattimore, T., Hutter, M., Gavane, V. (2011). Universal Prediction of Selected Bits. In: Kivinen, J., Szepesvári, C., Ukkonen, E., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2011. Lecture Notes in Computer Science(), vol 6925. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24412-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-24412-4_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24411-7
Online ISBN: 978-3-642-24412-4
eBook Packages: Computer ScienceComputer Science (R0)