The impact of automated decision-making systems on human lives is growing, emphasizing
the need for these systems to be not only accurate but also fair. The field of algorithmic …

As artificial intelligence (AI) rapidly approaches human-level performance in medical
imaging, it is crucial that it does not exacerbate or propagate healthcare disparities. Previous …

Machine learning (ML) systems often exhibit unexpectedly poor behavior when they are
deployed in real-world domains. We identify underspecification in ML pipelines as a key …

To avoid failures on out-of-distribution data, recent works have sought to extract features that
have an invariant or stable relationship with the label across domains, discarding" spurious" …

Abstract Machine learning (ML) holds great promise for improving healthcare, but it is critical
to ensure that its use will not propagate or amplify health disparities. An important step is to …

Many reinforcement learning (RL) applications have combinatorial action spaces, where
each action is a composition of sub-actions. A standard RL approach ignores this inherent …

The reliance of text classifiers on spurious correlations can lead to poor generalization at
deployment, raising concerns about their use in safety-critical domains such as healthcare …

By inferring latent groups in the training data, recent works introduce invariant learning to the
case where environment annotations are unavailable. Typically, learning group invariance …

In many prediction problems, spurious correlations are induced by a changing relationship
between the label and a nuisance variable that is also correlated with the covariates. For …

While machine learning models rapidly advance the state-of-the-art on various real-world
tasks, out-of-domain (OOD) generalization remains a challenging problem given the …