Invariant Risk Minimization Is A Total Variation Model

arXiv:2405.01389v1 Announce Type: new
Abstract: Invariant risk minimization (IRM) is an arising approach to generalize invariant features to different environments in machine learning. While most related works focus on new IRM settings or new application scenarios, the mathematical essence of IRM remains to be properly explained. We verify that IRM is essentially a total variation based on $L^2$ norm (TV-$\ell_2$) of the learning risk with respect to the classifier variable. Moreover, we propose a novel IRM framework based on the …

abstract application arxiv cs.lg environments explained features focus machine machine learning risk total type variation verify while