Abstract Machine learning models often perform poorly under subpopulation shifts in the data distribution. Developing methods that allow machine learning models to better …
Machine learning models often perform poorly on subgroups that are underrepresented in the training data. Yet, little is understood on the variation in mechanisms that cause …
S Santurkar, D Tsipras, A Madry - arXiv preprint arXiv:2008.04859, 2020 - arxiv.org
We develop a methodology for assessing the robustness of models to subpopulation shift--- specifically, their ability to generalize to novel data subpopulations that were not observed …
Importance weighting is a classic technique to handle distribution shifts. However, prior work has presented strong empirical and theoretical evidence demonstrating that importance …
Robustness to distribution shifts is critical for deploying machine learning models in the real world. Despite this necessity, there has been little work in defining the underlying …
Dealing with distribution shifts is one of the central challenges for modern machine learning. One fundamental situation is the covariate shift, where the input distributions of data change …
Skewed class proportions in real-world datasets present a challenge for machine learning algorithms, as they have a tendency to correctly categorize the majority class while …
Abstract Out-of-distribution (OOD) data poses serious challenges in deployed machine learning models, so methods of predicting a model's performance on OOD data without …
Handling an imbalanced class problem is a challenging task in real-world applications. This problem affects various prediction models that predict only the majority class and fail to …