The Risks and Rewards of Invariant Risk Minimization

Anonymous

Keywords: Machine Learning, Out-Of-Distribution Generalization, Causality

Abstract: Spurious correlations are one of the most prominent pain points for building and deploying machine learning models. Invariant Risk Minimization (IRM) is a learning algorithm designed to mitigate the effect of spurious features and perform well despite shifts in the test distribution. In this blog post, we discuss the motivation and details of IRM as well as it's criticisms and shortcomings.

ICLR Paper: https://arxiv.org/abs/2010.05761