Skip to main content

2015 | OriginalPaper | Buchkapitel

18. Justifying Information-Geometric Causal Inference

verfasst von : Dominik Janzing, Bastian Steudel, Naji Shajarisales, Bernhard Schölkopf

Erschienen in: Measures of Complexity

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Information-Geometric Causal Inference (IGCI) is a new approach to distinguish between cause and effect for two variables. It is based on an independence assumption between input distribution and causal mechanism that can be phrased in terms of orthogonality in information space. We describe two intuitive reinterpretations of this approach that make IGCI more accessible to a broader audience. Moreover, we show that the described independence is related to the hypothesis that unsupervised learning and semi-supervised learning only work for predicting the cause from the effect and not vice versa.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Fußnoten
1
Strictly speaking, this applies to the case of pattern recognition, and it is a little more complex for regression estimation.
 
2
For example, the task might be digit recognition, but the Universum points are letters.
 
3
Note that marginalization of \(P_{X\rightarrow Y}(\mathbf{x},f,\mathbf{y})\) to \(\mathbf{x},\mathbf{y}\) yields the same distribution as in Sect. 18.3 up to the technical modifications of having fixed endpoints and surjective functions.
 
4
Note that more precise statements would require lower bounds on \(\log \overrightarrow{p}^f\) and upper bounds on \(p_Y\), which goes beyond the scope of this chapter.
 
Literatur
1.
Zurück zum Zitat Amari, S., Nagaoka, H.: Methods of Information Geometry. Oxford University Press, New York (1993) Amari, S., Nagaoka, H.: Methods of Information Geometry. Oxford University Press, New York (1993)
2.
Zurück zum Zitat Chapelle, O., Schölkopf, B., Zien, A.: Semi-supervised Learning. MIT Press, Cambridge (2010) Chapelle, O., Schölkopf, B., Zien, A.: Semi-supervised Learning. MIT Press, Cambridge (2010)
3.
Zurück zum Zitat Cover, T., Thomas, J.: Elements of Information Theory. Wiley Series in Telecommunications. Wiley, New York (1991)CrossRefMATH Cover, T., Thomas, J.: Elements of Information Theory. Wiley Series in Telecommunications. Wiley, New York (1991)CrossRefMATH
4.
Zurück zum Zitat Daniušis, P., Janzing, D., Mooij, J., Zscheischler, J., Steudel, B., Zhang, K., Schölkopf, B.: Inferring deterministic causal relations. In: Proceedings of the Twenty Sixth Conference on Uncertainty in Artificial Intelligence (UAI), pp. 143–150. AUAI, Corvallis (2010) Daniušis, P., Janzing, D., Mooij, J., Zscheischler, J., Steudel, B., Zhang, K., Schölkopf, B.: Inferring deterministic causal relations. In: Proceedings of the Twenty Sixth Conference on Uncertainty in Artificial Intelligence (UAI), pp. 143–150. AUAI, Corvallis (2010)
5.
Zurück zum Zitat Hoyer, P., Janzing, D., Mooij, J., Peters, J., Schölkopf, B.: Nonlinear causal discovery with additive noise models. In: Koller, D., Schuurmans, D., Bengio, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems 21 (NIPS 2008), pp. 689–696. MIT Press, Cambridge (2009) Hoyer, P., Janzing, D., Mooij, J., Peters, J., Schölkopf, B.: Nonlinear causal discovery with additive noise models. In: Koller, D., Schuurmans, D., Bengio, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems 21 (NIPS 2008), pp. 689–696. MIT Press, Cambridge (2009)
6.
Zurück zum Zitat Janzing, D., Mooij, J., Zhang, K., Lemeire, J., Zscheischler, J., Daniušis, P., Steudel, B., Schölkopf, B.: Information-geometric approach to inferring causal directions. Artif. Intell. 182–183, 1–31 (2012)CrossRef Janzing, D., Mooij, J., Zhang, K., Lemeire, J., Zscheischler, J., Daniušis, P., Steudel, B., Schölkopf, B.: Information-geometric approach to inferring causal directions. Artif. Intell. 182–183, 1–31 (2012)CrossRef
7.
Zurück zum Zitat Janzing, D., Schölkopf, B.: Causal inference using the algorithmic Markov condition. IEEE Trans. Inf. Theory 56(10), 5168–5194 (2010)CrossRef Janzing, D., Schölkopf, B.: Causal inference using the algorithmic Markov condition. IEEE Trans. Inf. Theory 56(10), 5168–5194 (2010)CrossRef
8.
Zurück zum Zitat Lemeire, J., Janzing, D.: Replacing causal faithfulness with algorithmic independence of conditionals. Minds Mach. 23(2), 227–249 (2013)CrossRef Lemeire, J., Janzing, D.: Replacing causal faithfulness with algorithmic independence of conditionals. Minds Mach. 23(2), 227–249 (2013)CrossRef
9.
Zurück zum Zitat Li, M., Vitányi, P.: An Introduction to Kolmogorov Complexity and Its Applications. Springer, New York (1997) (3rd edn. 2008) Li, M., Vitányi, P.: An Introduction to Kolmogorov Complexity and Its Applications. Springer, New York (1997) (3rd edn. 2008)
10.
Zurück zum Zitat Pearl, J.: Causality: Models, Reasoning, and Inference. Cambridge University Press, Cambridge (2000) Pearl, J.: Causality: Models, Reasoning, and Inference. Cambridge University Press, Cambridge (2000)
11.
Zurück zum Zitat Peters, J., Janzing, D., Schölkopf, B.: Identifying cause and effect on discrete data using additive noise models. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010), Journal of Machine Learning Research: Workshop and Conference Proceedings, vol. 9, pp. 597–604 (2010) Peters, J., Janzing, D., Schölkopf, B.: Identifying cause and effect on discrete data using additive noise models. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010), Journal of Machine Learning Research: Workshop and Conference Proceedings, vol. 9, pp. 597–604 (2010)
12.
Zurück zum Zitat Peters, J., Janzing, D., Schölkopf, B.: Causal inference on discrete data using additive noise models. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2436–2450 (2011)CrossRef Peters, J., Janzing, D., Schölkopf, B.: Causal inference on discrete data using additive noise models. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2436–2450 (2011)CrossRef
13.
Zurück zum Zitat Peters, J., Mooij, J., Janzing, D., Schölkopf, B.: Identifiability of causal graphs using functional models. In: Proceedings of the Twenty Seventh Conference on Uncertainty in Artificial Intelligence (UAI), pp. 589–598. AUAI, Corvallis (2011) Peters, J., Mooij, J., Janzing, D., Schölkopf, B.: Identifiability of causal graphs using functional models. In: Proceedings of the Twenty Seventh Conference on Uncertainty in Artificial Intelligence (UAI), pp. 589–598. AUAI, Corvallis (2011)
14.
Zurück zum Zitat Schölkopf, B., Janzing, D., Peters, J., Sgouritsa, E., Zhang, K., Mooij, J.: On causal and anticausal learning. In: Proceedings of Twenty Ninth International Conference on Machine Learning (ICML 2012) (2012) Schölkopf, B., Janzing, D., Peters, J., Sgouritsa, E., Zhang, K., Mooij, J.: On causal and anticausal learning. In: Proceedings of Twenty Ninth International Conference on Machine Learning (ICML 2012) (2012)
15.
Zurück zum Zitat Sinz, F.H., Chapelle, O., Agarwal, A., Schölkopf, B.: An analysis of inference with the universum. In: Platt, J.C., Koller, D., Singer, Y., Roweis, S. (eds.) Advances in Neural Information Processing Systems 20 (NIPS 2007), pp. 1369–1376. MIT Press, Cambridge (2008) Sinz, F.H., Chapelle, O., Agarwal, A., Schölkopf, B.: An analysis of inference with the universum. In: Platt, J.C., Koller, D., Singer, Y., Roweis, S. (eds.) Advances in Neural Information Processing Systems 20 (NIPS 2007), pp. 1369–1376. MIT Press, Cambridge (2008)
16.
Zurück zum Zitat Spirtes, P., Glymour, C., Scheines, R.: Causation, Prediction, and Search. Lecture Notes in Statistics, vol. 81. Springer, New York (1993)CrossRefMATH Spirtes, P., Glymour, C., Scheines, R.: Causation, Prediction, and Search. Lecture Notes in Statistics, vol. 81. Springer, New York (1993)CrossRefMATH
17.
Zurück zum Zitat Vapnik, V.: Estimation of Dependences Based on Empirical Data. Statistics for Engineering and Information Science, 2nd edn. Springer, New York (2006)MATH Vapnik, V.: Estimation of Dependences Based on Empirical Data. Statistics for Engineering and Information Science, 2nd edn. Springer, New York (2006)MATH
18.
Zurück zum Zitat Weston, J., Collobert, R., Sinz, F., Bottou, L., Vapnik, V.: Inference with the universum. In: Proceedings of the Twenty Third International Conference on Machine learning (ICML), pp. 1009–1016. ACM (2006) Weston, J., Collobert, R., Sinz, F., Bottou, L., Vapnik, V.: Inference with the universum. In: Proceedings of the Twenty Third International Conference on Machine learning (ICML), pp. 1009–1016. ACM (2006)
19.
Zurück zum Zitat Zhang, K., Hyvärinen, A.: On the identifiability of the post-nonlinear causal model. In: Proceedings of the Twenty Fifth Conference on Uncertainty in Artificial Intelligence (UAI), pp. 647–655. AUAI, Corvallis (2009) Zhang, K., Hyvärinen, A.: On the identifiability of the post-nonlinear causal model. In: Proceedings of the Twenty Fifth Conference on Uncertainty in Artificial Intelligence (UAI), pp. 647–655. AUAI, Corvallis (2009)
Metadaten
Titel
Justifying Information-Geometric Causal Inference
verfasst von
Dominik Janzing
Bastian Steudel
Naji Shajarisales
Bernhard Schölkopf
Copyright-Jahr
2015
DOI
https://doi.org/10.1007/978-3-319-21852-6_18