Abstract
Algorithmic statistics studies explanations of observed data that are good in the algorithmic sense: an explanation should be simple i.e. should have small Kolmogorov complexity and capture all the algorithmically discoverable regularities in the data. However this idea can not be used in practice as is because Kolmogorov complexity is not computable.
In recent years resource-bounded algorithmic statistics were created [7, 8]. In this paper we prove a polynomial-time version of the following result of ‘classic’ algorithmic statistics.
Assume that some data were obtained as a result of some unknown experiment. What kind of data should we expect in similar situation (repeating the same experiment)? It turns out that the answer to this question can be formulated in terms of algorithmic statistics [6]. We prove a polynomial-time version of this result under a reasonable complexity theoretic assumption. The same assumption was used by Antunes and Fortnow [1].
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Antunes, L., Fortnow, L.: Worst-case running times for average-case algorithms. In: Proceedings of the 24th IEEE Conference on Computational Complexity, pp. 298–303 (2009)
Antunes, L., Fortnow, L., Vinodchandran, N.V.: Using depth to capture average-case complexity. In: Lingas, A., Nilsson, B.J. (eds.) FCT 2003. LNCS, vol. 2751, pp. 303–310. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-45077-1_28
Koppel, M.: Complexity, depth and sophistication. Complex Syst. 1, 1087–1091 (1987)
Kolmogorov, A.N.: Talk at the Information Theory Symposium in Tallinn, Estonia (then USSR) (1974)
Li, M., Vitányi, P.: An Introduction to Kolmogorov Complexity and Its Applications. TCS, vol. 3. Springer, New York (2008). https://doi.org/10.1007/978-0-387-49820-1
Milovanov, A.: Algorithmic statistic, prediction and machine learning. In: Proceedings of 33rd Symposium on Theoretical Aspects of Computer Science (STACS 2016). Leibnitz International Proceedings in Informatics (LIPIcs), vol. 47, pp. 54:1–54:13 (2016)
Milovanov, A.: On algorithmic statistics for space-bounded algorithms. In: Weil, P. (ed.) CSR 2017. LNCS, vol. 10304, pp. 232–244. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-58747-9_21
Milovanov A., Vereshchagin N.: Stochasticity in algorithmic statistics for polynomial time. In: 32nd Computational Complexity Conference (CCC 2017). Leibniz International Proceedings in Informatics (LIPIcs), vol. 79, pp. 17:1–17:18 (2017)
Shen, A.: Around kolmogorov complexity: basic notions and results. In: Vovk, V., Papadopoulos, H., Gammerman, A. (eds.) Measures of Complexity: Festschrift for Alexey Chervonenkis, pp. 75–115. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-21852-6_7. ISBN: 978-3-319-21851-9
Shen, A.: The concept of \((\alpha, \beta )\)-stochasticity in the Kolmogorov sense, and its properties. Sov. Math. Dokl. 271(1), 295–299 (1983)
Shen, A., Uspensky, V., Vereshchagin, N.: Kolmogorov Complexity and Algorithmic Randomness. ACM, New York (2017)
Stockmeyer, L.: On approximation algorithms for #P. SIAM J. Comput. 14(4), 849–861 (1985)
Vereshchagin, N., Shen, A.: Algorithmic statistics: forty years later. In: Day, A., Fellows, M., Greenberg, N., Khoussainov, B., Melnikov, A., Rosamond, F. (eds.) Computability and Complexity. LNCS, vol. 10010, pp. 669–737. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-50062-1_41
Vereshchagin, N., Vitányi, P.M.B.: Kolmogorov’s structure functions with an application to the foundations of model selection. IEEE Trans. Inf. Theory 50(12), 3265–3290 (2004). Preliminary Version: Proceedings of 47th IEEE Symposium on the Foundations of Computer Science, pp. 751–760 (2002)
Vereshchagin, N., Vitányi, P.M.B.: Rate distortion and denoising of individual data using Kolmogorov complexity. IEEE Trans. Inf. Theory 56(7), 3438–3454 (2010)
Acknowledgments
This work is supported in parts by the RFBR grant 16-01-00362, by the Young Russian Mathematics award, MK-5379.2018.1 and the RaCAF ANR-15-CE40-0016-01 grant. The study has also been funded by the Russian Academic Excellence Project ‘5-100’.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Milovanov, A. (2018). Algorithmic Statistics and Prediction for Polynomial Time-Bounded Algorithms. In: Manea, F., Miller, R., Nowotka, D. (eds) Sailing Routes in the World of Computation. CiE 2018. Lecture Notes in Computer Science(), vol 10936. Springer, Cham. https://doi.org/10.1007/978-3-319-94418-0_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-94418-0_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-94417-3
Online ISBN: 978-3-319-94418-0
eBook Packages: Computer ScienceComputer Science (R0)