Advertisement

Theory of Computing Systems

, Volume 58, Issue 3, pp 463–481 | Cite as

Algorithmic Minimal Sufficient Statistics: a New Approach

  • Nikolay VereshchaginEmail author
Article

Abstract

We introduce the notion of a strong sufficient statistic for a given data string. We show that strong sufficient statistics have better properties than just sufficient statistics. We prove that there are “strange” data strings, whose minimal strong sufficient statistic have much larger complexity than the minimal sufficient statistic.

Keywords

Algorithmic statistics Minimum description length Randomness deficiency Sufficient statistic Denoising 

Notes

Acknowledgments

The work was in part supported by the RFBR grant 12-01-00864 and the ANR grant ProjetANR-08-EMER-008 Moscow State University, National Research University Higher School of Economics (HSE)

References

  1. 1.
    Bauwens, B., Makhlin, A., Vereshchagin, N., Zimand, M.: Short lists with short programs in short time. ECCC report TR13-007. http://eccc.hpi-web.de/report/2013/007/
  2. 2.
    Gács, P., Tromp, J., Vitányi, P.M.B.: Algorithmic statistics. IEEE Trans. Inform. Th. 47(6), 2443–2463 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Kolmogorov, A.N.: Talk at the Information Theory Symposium in Tallinn. Estonia (1974)Google Scholar
  4. 4.
    Li, M., Vitányi, P.M.B.: An Introduction to Kolmogorov Complexity and its Applications, 2nd edn. Springer, New York (1997)CrossRefzbMATHGoogle Scholar
  5. 5.
    Shen, A.Kh.: Discussion on Kolmogorov complexity and statistical analysis. Comput. J. 42(4), 340–342 (1999)CrossRefzbMATHGoogle Scholar
  6. 6.
    Shen, A.: Game Arguments in computability theory and algorithmic information theory Proceedings of CiE, pp 655–666 (2012)Google Scholar
  7. 7.
    Vereshchagin, N.K., Vitányi, P.M.B.: Kolmogorov’s structure functions and model selection. IEEE Trans. Inf. Theory 50(12), 3265–3290 (2004)CrossRefzbMATHGoogle Scholar
  8. 8.
    Vereshchagin, N.: Algorithmic minimal sufficient statistic revisited. In: 5th Conference on Computability in Europe, CiE 2009, Proceedings, LNCS 5635, pp 478–487, Heidelberg (2009)Google Scholar
  9. 9.
    Vereshchagin, N.: On Algorithmic Strong Sufficient Statistics. In: 9th Conference on Computability in Europe, CiE 2013, Proceedings, LNCS 7921, pp 424–433, Milan (2013)Google Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Moscow State University, National Research University Higher School of Economics (HSE)MoscowRussian Federation

Personalised recommendations