The use of machine learning (ML) in healthcare raises numerous ethical concerns,
especially as models can amplify existing health inequities. Here, we outline ethical …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

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 …

Standard training via empirical risk minimization (ERM) can produce models that achieve
low error on average but high error on minority groups, especially in the presence of …

Artificial intelligence (AI) researchers and radiologists have recently reported AI systems that
accurately detect COVID-19 in chest radiographs. However, the robustness of these systems …

Deep classifiers are known to rely on spurious features—patterns which are correlated with
the target on the training data but not inherently relevant to the learning problem, such as the …

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 …

Abstract Machine learning algorithms typically assume that training and test examples are
drawn from the same distribution. However, distribution shift is a common problem in real …

We identify and formalize a fundamental gradient descent phenomenon resulting in a
learning proclivity in over-parameterized neural networks. Gradient Starvation arises when …

Distribution shifts—where the training distribution differs from the test distribution—can
substantially degrade the accuracy of machine learning (ML) systems deployed in the wild …