Generalization and Invariances in the Presence of Unobserved Confounding

The ability to extrapolate, or generalize, from observed to new related environments is central to any form of reliable machine learning, yet most methods fail when moving beyond $i.i.d$ data. In some cases, the reason lies in a misappreciation of the causal structure that governs the data, and in particular as a consequence of the influence of unobserved confounders that drive changes in observed distributions and distort correlations. In this paper, we argue for defining generalization with respect to a broader class of distribution shifts (defined as arising from interventions in the underlying causal model), including changes in observed, unobserved and target variable distributions. We propose a new robust learning principle that may be paired with any gradient-based learning algorithm. This learning principle has explicit generalization guarantees, and relates robustness with certain invariances in the causal model, clarifying why, in some cases, test performance lags training performance. We demonstrate the empirical performance of our approach on healthcare data from different modalities, including image and speech data.