Many research questions in Earth and environmental sciences are inherently causal,
requiring robust analyses to establish whether and how changes in one variable cause …

Deep learning has triggered the current rise of artificial intelligence and is the workhorse of
today's machine intelligence. Numerous success stories have rapidly spread all over …

Neural network classifiers can largely rely on simple spurious features, such as
backgrounds, to make predictions. However, even in these cases, we show that they still …

Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …

The two fields of machine learning and graphical causality arose and are developed
separately. However, there is, now, cross-pollination and increasing interest in both fields to …

A common approach to transfer learning under distribution shift is to fine-tune the last few
layers of a pre-trained model, preserving learned features while also adapting to the new …

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 …

Abstract Domain generalization (DG) is essentially an out-of-distribution problem, aiming to
generalize the knowledge learned from multiple source domains to an unseen target …

The goal of domain generalization algorithms is to predict well on distributions different from
those seen during training. While a myriad of domain generalization algorithms exist …

Learning robust models that generalize well under changes in the data distribution is critical
for real-world applications. To this end, there has been a growing surge of interest to learn …