Nonlinear Invariant Risk Minimization: A Causal Approach

no code implementations • 24 Feb 2021 • Chaochao Lu, Yuhuai Wu, Jośe Miguel Hernández-Lobato, Bernhard Schölkopf

Finally, in the discussion, we further explore the aforementioned assumption and propose a more general hypothesis, called the Agnostic Hypothesis: there exist a set of hidden causal factors affecting both inputs and outcomes.

BIG-bench Machine Learning Representation Learning