UvA-DARE ( Digital Academic Repository ) Causal Discovery with Continuous Additive Noise Models

By Jan Peters, Joris M. Mooij, Dominik Janzing, Dominik Janzing, Bernhard Schölkopf. 2014

682 citations recorded by the source corpus.

We consider the problem of learning causal directed acyclic graphs from an observational joint distribution. One can use these graphs to predict the outcome of interventional experiments, from which data are often not available. We show that if the observational distribution follows a structural equation model with an additive noise structure, the directed acyclic graph becomes identifiable from the distribution under mild conditions. This constitutes an interesting alternative to traditional methods that assume faithfulness and identify only the Markov equivalence class of the graph, thus leaving some edges undirected. We provide practical algorithms for finitely many samples, RESIT (regression with subsequent independence test) and two methods based on an independence score. We prove that RESIT is correct in the population setting and provide an empirical evaluation.

Subfields: Artificial Intelligence, Statistics and Probability, Causal Inference & Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Bernhard Schölkopf
  2. Yoshua Bengio
  3. Sergey Levine
  4. Mohit Bansal
  5. Quoc V. Le
  6. Percy Liang
  7. Jianfeng Gao
  8. Ruslan Salakhutdinov

In Statistics and Probability

  1. Bernhard Schölkopf
  2. Jan Peters
  3. David Lopez-Paz
  4. Arthur Gretton
  5. Kun Zhang
  6. Dominik Janzing
  7. Peter Buhlmann
  8. Dino Sejdinovic

In Causal Inference & Discovery

  1. Bernhard Schölkopf
  2. David Lopez-Paz
  3. Jan Peters
  4. Dominik Janzing
  5. Kun Zhang
  6. Joris M. Mooij
  7. Peter Buhlmann
  8. Stefan Bauer

Citations in the corpus