Towards a Learning Theory of Causation

371 views · Published 27 June 2016 · 22:24 · Indexed 27 October 2026

Channel: Microsoft Research · 2016 · Science & Technology

Watch on YouTube

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  × Y i  , and  l i   is a binary label indicating whether “ X i  to Y i  ” or “ X i  ≤ftarrow 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.

More from this channel