Toward Causal Representation Learning

Selected reading: Causal representation and additive-noise model assumptions.

How to study this source

• Can a model learn causes?

  commentaryCausal representation and additive-noise model assumptions

  Identify the proposed model class and what evidence could distinguish its causal account.

Ideas and questions

Read background definitions when a term blocks the argument. Then return to the source and reconstruct its claim in your own words.

Read alongside, read against

• Causal Inference: What If

  Hernán · Robins. Compare assumptions, evidence and scope with the source above. These are editorial companions, not necessarily direct responses.

• Invariant Risk Minimization

  Arjovsky et al.. Compare assumptions, evidence and scope with the source above. These are editorial companions, not necessarily direct responses.

• Causal inference by using invariant prediction: identification and confidence intervals

  Peters, Bühlmann · Meinshausen. Compare assumptions, evidence and scope with the source above. These are editorial companions, not necessarily direct responses.

• The Seven Tools of Causal Inference, with Reflections on Machine Learning

  Judea Pearl. Compare assumptions, evidence and scope with the source above. These are editorial companions, not necessarily direct responses.

• Nonlinear causal discovery with additive noise models

  Hoyer et al.. Compare assumptions, evidence and scope with the source above. These are editorial companions, not necessarily direct responses.