2021

On Invariance Penalties for Risk Minimization

Khezeli, Kia, Blaas, Arno, Soboczenski, Frank et al.

Understand

The Invariant Risk Minimization (IRM) principle was first proposed by Arjovsky et al.

  • [2019] to address the domain generalization problem by leveraging data heterogeneity from differing experimental conditions.
  • Specifically, IRM seeks to find a data representation under which an optimal classifier remains invariant across all domains.
  • Despite the conceptual appeal of IRM, the effectiveness of the originally proposed invariance penalty has recently been brought into question.

Reading the bibliography…