Abstract
We try to predict the next bit from a given finite binary string when the sequence is sampled from a computable probability measure on the Cantor space. There exists the best betting strategy among a class of effective ones up to a multiplicative constant, the induced prediction from which is called algorithmic probability or universal induction by Solomonoff. The prediction converges to the true induced measure for sufficiently random sequences. However, the prediction is not computable.
We propose a framework to study the properties of computable predictions. We prove that all sufficiently general computable predictions also converge to the true induced measure. The class of sequences along which the prediction converges is related to computable randomness. We also discuss the speed of the convergence. We prove that, even when a computable prediction predicts a computable sequence, the speed of the convergence cannot be bounded by a computable function monotonically decreasing to 0.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Downey, R.G., Hirschfeldt, D.R.: Algorithmic randomness and complexity. Theory and Applications of Computability. Springer, New York (2010). https://doi.org/10.1007/978-0-387-68441-3
Hutter, M.: Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Springer, Heidelberg (2005). https://doi.org/10.1007/b138233
Hutter, M., Muchnik, A.: On semimeasures predicting Martin-Löf random sequences. Theor. Comput. Sci. 382, 247–261 (2007)
Legg, S.: Machine super intelligence. Ph.D. thesis, Università della Svizzera italiana (2008)
Leike, J., Hutter, M.: Solomonoff induction violates Nicod’s criterion. In: Chaudhuri, K., Gentile, C., Zilles, S. (eds.) ALT 2015. LNCS (LNAI), vol. 9355, pp. 349–363. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24486-0_23
Levin, L.A.: On the notion of a random sequence. Sov. Math. Dokl. 14, 1413–1416 (1973)
Li, M., Vitányi, P.: An introduction to Kolmogorov complexity and its applications. Graduate Texts in Computer Science, 3rd edn. Springer, New York (2009). https://doi.org/10.1007/978-0-387-49820-1
Nies, A.: Computability and Randomness. Oxford Logic Guides, vol. 51. Oxford University Press, Oxford (2009). https://doi.org/10.1093/acprof:oso/9780199230761.001.0001
Rute, J.: Computable randomness and betting for computable probability spaces. Math. Log. Q. 62(4–5), 335–366 (2016)
Soare, R.I.: Turing Computability. Theory and Applications of Computability. Springer, Heidelberg (2016). https://doi.org/10.1007/978-3-642-31933-4
Solomonoff, R.J.: Complexity-based induction systems: comparisons and convergence theorems. IEEE Trans. Inf. Theor. IT-24, 422–432 (1978)
Zeugmann, T., Zilles, S.: Learning recursive functions: a survey. Theor. Comput. Sci. 397, 4–56 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Miyabe, K. (2019). Computable Prediction. In: Hammer, P., Agrawal, P., Goertzel, B., Iklé, M. (eds) Artificial General Intelligence. AGI 2019. Lecture Notes in Computer Science(), vol 11654. Springer, Cham. https://doi.org/10.1007/978-3-030-27005-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-27005-6_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27004-9
Online ISBN: 978-3-030-27005-6
eBook Packages: Computer ScienceComputer Science (R0)