English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Distinguishing Between Cause and Effect via Kernel-Based Complexity Measures for Conditional Distributions

MPS-Authors
/persons/resource/persons84243

Sun,  X
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
biological cy;

/persons/resource/persons84193

Schölkopf,  B
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
biological cy;

Fulltext (public)

ESANN-2007-Sun.pdf
(Any fulltext), 683KB

Supplementary Material (public)
There is no public supplementary material available
Citation

Sun, X., Janzing, D., & Schölkopf, B. (2007). Distinguishing Between Cause and Effect via Kernel-Based Complexity Measures for Conditional Distributions. In M. Verleysen (Ed.), Advances in computational intelligence and learning: 15th European Symposium on Artificial Neural Networks: ESANN 2007 (pp. 441-446). Evere, Belgium: D-Side Publications.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-CE19-C
Abstract
We propose a method to evaluate the complexity of probability measures from data that is based on a reproducing kernel Hilbert space seminorm of the logarithm of conditional probability densities. The motivation is to provide a tool for a causal inference method which assumes that conditional probabilities for effects given their causes are typically simpler and smoother than vice-versa. We present experiments with toy data where the quantitative results are consistent with our intuitive understanding of complexity and smoothness. Also in some examples with real-world data the probability measure corresponding to the true causal direction turned out to be less complex than those of the reversed order.