Advertisement

Statistical Asymmetries Between Cause and Effect

Chapter
Part of the Tutorials, Schools, and Workshops in the Mathematical Sciences book series (TSWMS)

Abstract

Recent progress in the field of machine learning suggests that the joint distribution of two variables X, Y sometimes contains information about the underlying causal structure, e.g., whether X is the case of Y or Y the cause of X, given that exactly one of the alternatives is true. To provide an idea about these statistical asymmetries I show some intuitive examples, both hypothetical toy scenarios as well as scatter plots from real world data. I sketch some recent approaches to infer the causal direction based on these asymmetries and give some pointers to physics literature that relate them to the thermodynamic arrow of time.

References

  1. 1.
    H. Reichenbach, The Direction of Time (University of California Press, Berkeley, 1956)Google Scholar
  2. 2.
    Database with Cause-Effect Pairs, https://webdav.tuebingen.mpg.de/cause-effect/. Copyright Information for each Cause-Effect Pair is contained in the respective description file
  3. 3.
    J.M. Mooij, J. Peters, D. Janzing, J. Zscheischler, B. Schölkopf, Distinguishing cause from effect using observational data: methods and benchmarks. J. Mach. Learn. Res. 17(32), 1–102 (2016)MATHMathSciNetGoogle Scholar
  4. 4.
    M. Leifer, R. Spekkens, Towards a formulation of quantum theory as a causally neutral theory of Bayesian inference. Phys. Rev. A(88), 052130 (2013)Google Scholar
  5. 5.
    K. Ried, M. Agnew, L. Vermeyden, D. Janzing, R. Spekkens, K. Resch, A quantum advantage for inferring causal structure. Nat. Phys. 11(5), 414–420 (2015)CrossRefGoogle Scholar
  6. 6.
    P. Spirtes, C. Glymour, R. Scheines, Causation, Prediction, and Search. Lecture Notes in Statistics (Springer, New York, 1993)Google Scholar
  7. 7.
    J. Pearl, Causality (Cambridge University Press, Cambridge, 2000)MATHGoogle Scholar
  8. 8.
    C. Wood, R. Spekkens, The lesson of causal discovery algorithms for quantum correlations: causal explanations of bell-inequality violations require fine-tuning. New J. Phys. 17(3), 033002 (2015)Google Scholar
  9. 9.
    D. Janzing, X. Sun, B. Schölkopf, Distinguishing cause and effect via second order exponential models. http://arxiv.org/abs/0910.5561 (2009)
  10. 10.
    D. Janzing, B. Schölkopf, Causal inference using the algorithmic Markov condition. IEEE Trans. Inform. Theory 56(10), 5168–5194 (2010)CrossRefMATHMathSciNetGoogle Scholar
  11. 11.
    J. Lemeire, D. Janzing, Replacing causal faithfulness with algorithmic independence of conditionals. Minds Mach. 23(2), 227–249 (2012)CrossRefGoogle Scholar
  12. 12.
    M. Li, P. Vitányi. An Introduction to Kolmogorov Complexity and Its Applications (Springer, New York, 1997) (3rd edition: 2008).CrossRefMATHGoogle Scholar
  13. 13.
    D. Janzing, R. Chaves, B. Schölkopf, Algorithmic independence of initial condition and dynamical law in thermodynamics and causal inference. New J. Phys. 18(093052), 1–13 (2016)Google Scholar
  14. 14.
    J. Mooij, D. Janzing, J. Peters, B. Schölkopf, Regression by dependence minimization and its applications to causal inference in additive noise models, in Proceedings of the 26th International Conference on Machine Learning, Montreal, ACM International Conference Proceeding Series, New York, pp. 745–752 (2009)Google Scholar
  15. 15.
    Y. Kano, S. Shimizu, Causal inference using nonnormality, in Proceedings of the International Symposium on Science of Modeling, the 30th Anniversary of the Information Criterion, Tokyo, pp. 261–270 (2003)Google Scholar
  16. 16.
    P. Hoyer, D Janzing, J. Mooij, J. Peters, B Schölkopf, Nonlinear causal discovery with additive noise models, in Proceedings of the Conference Neural Information Processing Systems (NIPS) 2008, ed. by D. Koller, D. Schuurmans, Y. Bengio, L. Bottou (MIT Press, Vancouver, 2009)Google Scholar
  17. 17.
    J.M. Mooij, J. Peters, D. Janzing, J. Zscheischler, B. Schölkopf, Distinguishing cause from effect using observational data: methods and benchmarks. J. Mach. Learn. Res. 17(32), 1–102 (2016)MATHMathSciNetGoogle Scholar
  18. 18.
    D. Janzing, B. Steudel, Justifying additive-noise-based causal discovery via algorithmic information theory. Open Syst. Inform. Dyn. 17(2), 189–212 (2010)CrossRefMATHMathSciNetGoogle Scholar
  19. 19.
    J. Peters, D. Janzing, A. Gretton, B. Schölkopf, Detecting the direction of causal time series, in Proceedings of the 26th International Conference on Machine Learning, ACM International Conference Proceeding Series, Montreal, vol. 382 (ACM, New York, 2009), pp. 801–808Google Scholar
  20. 20.
    D. Janzing, On the entropy production of time series with unidirectional linearity. J. Stat. Phys. 138, 767–779 (2010)ADSCrossRefMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Max Planck Institute for Intelligent SystemsTübingenGermany

Personalised recommendations