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.
翻译:在本文中,我们介绍了对Arjovsky等人(2020年)提出的线性综合管理框架(IRMV1)的受控研究,我们表明,在对最佳递减器进行小改动的情况下,IRMv1(及其变异体)框架可能不稳定,这尤其可能导致对新环境的更糟糕的概括化,即使与机构风险管理相比,机构风险管理只是将所有培训环境结合在一起的全球最低要求趋同。我们还强调了在IRMv1设置中扩大规模的问题。这些观察突出了严格评估的重要性以及单位测试对于衡量实现IRM的进展的重要性。