Abstract
Kolmogorov complexity measures the amount of information in data, but does not distinguish structure from noise. Kolmogorov’s definition of the structure function was the first attempt to measure only the structural information in data, by measuring the complexity of the smallest model that allows for optimal compression of the data. Since then, many variations of this idea have been proposed, for which we use sophistication as an umbrella term. We describe two fundamental problems with existing proposals, showing many of them to be unsound. Consequently, we put forward the view that the problem is fundamental: it may be impossible to objectively quantify the sophistication.
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
Adriaans, P.: Facticity as the amount of self-descriptive information in a data set (2012). arXiv:1203.2245
Antunes, L., Fortnow, L., van Melkebeek, D., Vinodchandran, N.V.: Computational depth: concept and applications. Th. Comp. Sc. 354(3), 391–404 (2006)
Antunes, L.F.C., Bauwens, B., Souto, A., Teixeira, A.: Sophistication vs logical depth (2013). http://arxiv.org/abs/1304.8046
Antunes, L.F.C., Fortnow, L.: Sophistication revisited. Theory Comput. Syst. 45(1), 150–161 (2009)
Bennett, C.H.: Logical depth and physical complexity. In: The Universal Turing Machine: A Half-Century Survey. Oxford University Press (1988)
Bloem, P., Mota, F., de Rooij, S., Antunes, L., Adriaans, P.: A safe approximation for kolmogorov complexity. In: Auer, P., Clark, A., Zeugmann, T., Zilles, S. (eds.) ALT 2014. LNCS, vol. 8776, pp. 336–350. Springer, Heidelberg (2014)
Cover, T.M.: Kolmogorov complexity, data compression, and inference. In: The Impact of Processing Techniques on Communications, pp. 23–33. Springer (1985)
Gács, P., Tromp, J., Vitányi, P.M.B.: Algorithmic statistics. IEEE Tr. Inf. Th. 47(6), 2443–2463 (2001)
Gell-Mann, M., Lloyd, S.: Information measures, effective complexity, and total information. Complexity 2(1), 44–52 (1996)
Gell-Mann, M., Lloyd, S.: Effective complexity. Nonextensive Entropy-Interdisciplinary Applications, by Edited by Murray Gell-Mann and C Tsallis, pp. 440. Oxford University Press, Apr 2004. ISBN-10: 0195159764. ISBN-13: 9780195159769, 1 (2004)
Grünwald, P., Vitányi, P.M.B.: Shannon information and Kolmogorov complexity (2004). arXiv:cs/0410002
Kleene, S.C.: On notation for ordinal numbers. J. Symb. Log., 150–155 (1938)
Koppel, M.: Structure. In: The Universal Turing Machine: A Half-Century Survey. Oxford University Press (1988)
Koppel, M., Atlan, H.: An almost machine-independent theory of program-length complexity, sophistication, and induction. Inf. Sci. 56(1–3), 23–33 (1991)
Li, M., Vitányi, P.M.B.: An introduction to Kolmogorov complexity and its applications. Springer-Verlag (1993)
Mota, F., Aaronson, S., Antunes, L., Souto, A.: Sophistication as randomness deficiency. In: Jurgensen, H., Reis, R. (eds.) DCFS 2013. LNCS, vol. 8031, pp. 172–181. Springer, Heidelberg (2013)
Shen, A.K.: The concept of (\(\alpha \), \(\beta \))-stochasticity in the Kolmogorov sense, and its properties. Soviet Math. Dokl 28(1), 295–299 (1983)
Vereshchagin, N.: Algorithmic minimal sufficient statistics: a new approach. Theory of Computing Systems, 1–19 (2015)
Vereshchagin, N.K., Vitányi, P.M.B.: Kolmogorov’s structure functions and model selection. IEEE Tr. Inf. Th. 50(12), 3265–3290 (2004)
Vitányi, P.M.B.: Meaningful information. IEEE Tr. Inf. Th. 52(10) (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Bloem, P., de Rooij, S., Adriaans, P. (2015). Two Problems for Sophistication. In: Chaudhuri, K., GENTILE, C., Zilles, S. (eds) Algorithmic Learning Theory. ALT 2015. Lecture Notes in Computer Science(), vol 9355. Springer, Cham. https://doi.org/10.1007/978-3-319-24486-0_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-24486-0_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24485-3
Online ISBN: 978-3-319-24486-0
eBook Packages: Computer ScienceComputer Science (R0)