# A call for better unit testing for invariant risk minimisation

arXiv: https://arxiv.org/abs/2106.03234 · HTML: https://mlsanity.com/paper/2106.03234/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 6 Jun 2021.

## Builds on (most cited first, 10 of 10)

- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Does Invariant Risk Minimization Capture Invariance?](https://mlsanity.com/paper/2101.01134/) (2021)
- [When is invariance useful in an Out-of-Distribution Generalization problem ?](https://mlsanity.com/paper/2008.01883/) (2020)
- [Does Distributionally Robust Supervised Learning Give Robust Classifiers?](https://mlsanity.com/paper/1611.02041/) (2016)
- [Linear unit-tests for invariance discovery](https://mlsanity.com/paper/2102.10867/) (2021)
- [Linear Regression Games: Convergence Guarantees to Approximate Out-of-Distribution Solutions](https://mlsanity.com/paper/2010.15234/) (2020)
- [Feature Noise Induces Loss Discrepancy Across Groups](https://mlsanity.com/paper/1911.09876/) (2019)

## Abstract (arXiv)

In this paper we present a controlled study on the linearized IRM framework (IRMv1) introduced in Arjovsky et al. (2020). We show that IRMv1 (and its variants) framework can be potentially unstable under small changes to the optimal regressor. This can, notably, lead to worse generalisation to new environments, even compared with ERM which converges simply to the global minimum for all training environments mixed up all together. We also highlight the isseus of scaling in the the IRMv1 setup. These observations highlight the importance of rigorous evaluation and importance of unit-testing for measuring progress towards IRM.