Malign Overfitting: Interpolation and Invariance are Fundamentally at Odds

Learned classifiers should often possess certain invariance properties meant to encourage fairness, robustness, or out-of-distribution generalization. However, multiple recent works empirically demonstrate that common invariance-inducing regularizers are ineffective in the over-parameterized regime, in which classifiers perfectly fit (i.e. interpolate) the training data. This suggests that the phenomenon of ``benign overfitting", in which models generalize well despite interpolating, might not favorably extend to settings in which robustness or fairness are desirable. In this work we provide a theoretical justification for these observations. We prove that - even in the simplest of settings - any interpolating classifier (with nonzero margin) will not satisfy these invariance properties. We then propose and analyze an algorithm that - in the same setting - successfully learns a non-interpolating classifier that is provably invariant. We validate our theoretical observations regarding the conflict between interpolation and invariance on simulated data and the Waterbirds dataset.