ICML 2015poster229 citations

Towards a Learning Theory of Cause-Effect Inference

David Lopez-Paz, Krikamol Muandet, Bernhard Schölkopf, Iliya Tolstikhin

Abstract

We pose causal inference as the problem of learning to classify probability distributions. In particular, we assume access to a collection {(S_i,l_i)}_i=1^n, where each S_i is a sample drawn from the probability distribution of X_i \times Y_i, and l_i is a binary label indicating whether “X_i \to Y_i” or “X_i ←Y_i”. Given these data, we build a causal inference rule in two steps. First, we featurize each S_i using the kernel mean embedding associated with some characteristic kernel. Second, we train a binary classifier on such embeddings to distinguish between causal directions. We present generalization bounds showing the statistical consistency and learning rates of the proposed approach, and provide a simple implementation that achieves state-of-the-art cause-effect inference. Furthermore, we extend our ideas to infer causal relationships between more than two variables.

BibTeX
@InProceedings{pmlr-v37-lopez-paz15,
  title = 	 {Towards a Learning Theory of Cause-Effect Inference},
  author = 	 {Lopez-Paz, David and Muandet, Krikamol and Schölkopf, Bernhard and Tolstikhin, Iliya},
  booktitle = 	 {Proceedings of the 32nd International Conference on Machine Learning},
  pages = 	 {1452--1461},
  year = 	 {2015},
  editor = 	 {Bach, Francis and Blei, David},
  volume = 	 {37},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Lille, France},
  month = 	 {07--09 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v37/lopez-paz15.pdf},
  url = 	 {https://proceedings.mlr.press/v37/lopez-paz15.html},
  abstract = 	 {We pose causal inference as the problem of learning to classify probability distributions. In particular, we assume access to a collection {(S_i,l_i)}_i=1^n, where each S_i is a sample drawn from the probability distribution of X_i \times Y_i, and l_i is a binary label indicating whether “X_i \to Y_i” or “X_i ←Y_i”. Given these data, we build a causal inference rule in two steps. First, we featurize each S_i using the kernel mean embedding associated with some characteristic kernel. Second, we train a binary classifier on such embeddings to distinguish between causal directions. We present generalization bounds showing the statistical consistency and learning rates of the proposed approach, and provide a simple implementation that achieves state-of-the-art cause-effect inference. Furthermore, we extend our ideas to infer causal relationships between more than two variables.}
}
Towards a Learning Theory of Cause-Effect Inference · ICML 2015