Towards a learning theory of cause-effect inference

32nd International Conference on Machine Learning, ICML 2015

Volumn 2, Issue , 2015, Pages 1452-1461

  Lopez Paz, David ^a,b   Muandet, Krikamoi ^a   Schölkopf, Bernhard ^a   Tolstikhin, Ilya ^a  

^a MAX PLANCK INSTITUTE FOR INTELLIGENT SYSTEMS   (Germany)

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; LEARNING SYSTEMS;

BINARY CLASSIFIERS; CAUSAL INFERENCES; CAUSAL RELATIONSHIPS; GENERALIZATION BOUND; LEARNING RATES; LEARNING THEORY; STATE OF THE ART; STATISTICAL CONSISTENCIES;

PROBABILITY DISTRIBUTIONS;

EID: 84965164729     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (48)

1. Bartlett, P. L. and Mendelson, S. Rademacher and Gaussian complexities: Risk bounds and structural results. JMLR, 2002.
2. Bartlett, P. L. and Mendelson, S. Empirical minimization. Probability Theory and Related Fields, 135(4), 2006.
3. Bartlett, P. L., Bousquet, O., and Mendelson, S. Local rademacher complexities. The Annals of Statistics, 33(4), 2005.
4. Bartlett, P. L., Jordan, M. I., and McAuliffe, J. D. Convexity, classification, and risk bounds. Journal of the American Statistical Association, 101, 2006.
5. Berlinet, A. and Thomas-Agnan, C. Reproducing Kernel Hilbert Spaces in Probability and Statistics. Kluwer Academic Publishers, 2004.
6. Blankertz, B. BCI Competition III data, experiment 4a, subject 3, 1000Hz, 2005. URL http://bbci.de/competition/iii/download/.
7. Boucheron, Stéphane, Lugosi, Gábor, and Bousquet, Olivier. Theory of classification: a survey of recent advances. ESAIM: Probability and Statistics, 2005.
8. Cuturi, M., Fukumizu, K., and Vert, J. P. Semigroup kernels on measures. JMLR, 2005.
9. Daniusis, P., Janzing, D., Mooij, J., Zscheischler, J., Steudel, B., Zhang, K., and Schölkopf, B. Inferring deterministic causal relations. UAI, 2012.
10. Guyon, I. Cause-effect pairs kaggle competition, 2013. URL https://www.kaggle.com/c/cause-effect-pairs/.
11. Guyon, I. Chalearn fast causation coefficient challenge, 2014. URL https://www.codalab.org/competitions/1381.
12. Hein, M. and Bousquet, O. Hilbertian metrics and positive definite kernels on probability measures. AISTATS, 2004.
13. Hoyer, P. O., Janzing, D., Mooij, J. M., Peters, J. R., and Schölkopf, B. Nonlinear causal discovery with additive noise models. NIPS, 2009.
14. Janzing, D., Mooij, J., Zhang, K., Lemeire, J., Zscheischler, J., Daniušis, P., Steudel, B., and Schölkopf, B. Information-geometric approach to inferring causal directions. Artificial Intelligence, 2012.
15. Janzing, D., Steudel, B., Shajarisales, N., and Schölkopf, B. Justifying information-geometric causal inference. arXiv, 2014.
16. Jebara, T., Kondor, R., and Howard, A. Probability product kernels. JMLR, 2004.
17. Koltchinskii, V. Oracle Inequalities in Empirical Risk Minimization and Sparse Recovery Problems. Ecole d'été de probabilités de Saint-Flour. Springer, 2011.
18. Koltchinskii, V. and Panchenko, D. Rademacher processes and bounding the risk of function learning. In E. Gine, D. and J.Wellner (eds.), High Dimensional Probability, II, pp. 443-457. Birkhauser, 1999.
19. Kpotufe, S., Sgouritsa, E., Janzing, D., and Scholkopf, B. Consistency of causal inference under the additive noise model. ICML, 2013.
20. Ledoux, M. and Talagrand, M. Probability in Banach Spaces: Isoperimetry and Processes. Springer, 1991.
21. Lichman, M. UCI machine learning repository, 2013. URL http://archive.ics.uci.edu/ml.
22. Martins, A. F. T., Smith, N. A., Xing, E. P., Aguiar, P. M. Q., and Figueiredo, M. A. T. Nonextensive information theoretic kernels on measures. JMLR, 2009.
23. Maurer, A. The rademacher complexity of linear transformation classes. COLT, 2006.
24. Mooij, J. M., Peters, J., Janzing, D., Zscheischler, J., and Schölkopf, B. Distinguishing cause from effect using observational data: methods and benchmarks. arXiv preprint arXiv:1412.3773, 2014.
25. Muandet, K., Fukumizu, K., Dinuzzo, F., and Schölkopf, B. Learning from distributions via support measure machines. NIPS, 2012.
26. Pearl, J. Causality: models, reasoning and inference. Cambridge Univ Press, 2000.
27. Peters, J., Janzing, D., Gretton, A., and Schölkopf, B. Detecting the direction of causal time series. ICML, 2009.
28. Peters, J., M., Joris M., Janzing, D., and Schölkopf, B. Causal discovery with continuous additive noise models. JMLR, 2014.
29. Rahimi, A. and Recht, B. Random features for large-scale kernel machines. NIPS, 2007.
30. Rahimi, A. and Recht, B. Weighted sums of random kitchen sinks: Replacing minimization with randomization in learning. NIPS, 2008.
31. Reed, M. and Simon, B. Methods of modern mathematical physics, vol. 1. Functional analysis, volume 1. Academic press New York, 1972.
32. Reichenbach, H. The Direction of Time. Dover, 1956.
33. Rudin, W. Fourier Analysis on Groups. Wiley, 1962.
34. Schölkopf, B. and Smola, A. J. Learning with Kernels. MIT Press, 2002.
35. Schölkopf, B., Janzing, D., Peters, J., Sgouritsa, E., Zhang, K., and Mooij, J. On causal and anticausal learning. ICML, 2012.
36. Schölkopf, B., Janzing, D., Peters, J., Sgouritsa, E., Zhang, K., and Mooij, J. M. On causal and anticausal learning. In ICML, 2012.
37. Shimizu, S., Hoyer, P. O., Hyvärinen, A., and Kerminen, A. A linear non-Gaussian acyclic model for causal discovery. JMLR, 2006.
38. Shimizu, S., Inazumi, T., Sogawa, Y., Hyvärinen, A., Kawa-hara, Y., Washio, T., Hoyer, P. O., and Bollen, K. Di-rectlingam: A direct method for learning a linear non-gaussian structural equation model. JMLR, 2011.
39. Smola, A. J., Gretton, A., Song, L., and Schölkopf, B. A Hilbert space embedding for distributions. In ALT. Springer-Verlag, 2007.
40. Song, L. Learning via Hilbert Space Embedding of Distributions. PhD thesis, The University of Sydney, 2008.
41. Spirtes, P., Glymour, C. N., and Scheines, R. Causation, prediction, and search. MIT Press, 2000.
42. Sriperumbudur, B. K., Gretton, A., Fukumizu, K., Schölkopf, B., and Lanckriet, G. Hilbert space embeddings and metrics on probability measures. JMLR, 2010.
43. Stegle, O., Janzing, D., Zhang, K., Mooij, J. M., and Schölkopf, B. Probabilistic latent variable models for distinguishing between cause and effect. NIPS, 2010.
44. Steinwart, I. and Christmann, A. Support vector machines. Springer, 2008.
45. Szabó, Z., Sriperumbudur, B., Póczos, B., and Gretton, A. Learning theory for distribution regression. arXiv, 2014.
46. Vapnik, V. N. Statistical Learning Theory. John Wiley & Sons, 1998.
47. Zhang, K. and Hyvärinen, A. On the identifiability of the post-nonlinear causal model. UAI, 2009.
48. Zscheischler, J. Benchmark data set for causal discovery algorithms, v0.8, 2014. URL http://webdav. tuebingen. mpg.de/cause-effect/.