Towards a Learning Theory of Cause-Effect Inference

MaRDI QIDQ6258913zbMATH OpenFDO

Authors David Lopez-Paz, Krikamol Muandet, Bernhard Schölkopf, Ilya Tolstikhin

Publication date 9 February 2015

Has companion code repository https://github.com/lopezpaz/causation_learning_theory

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 $X_{i}imes{Y}_i$, and $l_i$ is a binary label indicating whether "$X_{i}o{Y}_i$" or "$X_{i}leftarrow{Y}_i$". 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.

This page was built for publication: Towards a Learning Theory of Cause-Effect Inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6258913)