We consider the problem of training a classification model with group annotated training
data. Recent work has established that, if there is distribution shift across different groups …

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 …

Distributionally robust optimization (DRO) can improve the robustness and fairness of
learning methods. In this paper, we devise stochastic algorithms for a class of DRO …

Models trained via empirical risk minimization (ERM) are known to rely on spurious
correlations between labels and task-independent input features, resulting in poor …

Generalising robustly to distribution shift is a major challenge that is pervasive across most
real-world applications of machine learning. A recent study highlighted that many advanced …

While neural networks have shown remarkable success on classification tasks in terms of
average-case performance, they often fail to perform well on certain groups of the data. Such …

A central goal of machine learning is to learn robust representations that capture the
fundamental relationship between inputs and output labels. However, minimizing training …

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 …

Many machine learning tasks involve subpopulation shift where the testing data distribution
is a subpopulation of the training distribution. For such settings, a line of recent work has …

This paper investigates group distributionally robust optimization (GDRO), with the purpose
to learn a model that performs well over $ m $ different distributions. First, we formulate …