MPI für biologische Kybernetik / Biologische Kybernetik |
|Telling cause from effect based on high-dimensional observations|
|Authors:||Janzing, D.; Hoyer, P.; Schölkopf, B.|
|Editors:||Fürnkranz, J.; Joachims, T.|
|Date of Publication (YYYY-MM-DD):||2010-06|
|Title of Proceedings:||Proceedings of the 27th International Conference on Machine Learning (ICML 2010)|
|Intended Educational Use:||No|
|Abstract / Description:||We describe a method for inferring linear causal relations|
among multi-dimensional variables. The idea is to use an asymmetry between the distributions of cause and effect that occurs
if the covariance matrix of the cause and the structure matrix mapping the cause
to the effect are independently chosen.
The method applies to both stochastic and deterministic causal relations, provided that the dimensionality is sufficiently high (in some experiments, 5 was enough). It is applicable to Gaussian as well as non-Gaussian data.
|External Publication Status:||published|
|Communicated by:||Holger Fischer|
|Affiliations:||MPI für biologische Kybernetik/Empirical Inference (Dept. Schölkopf)|