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 …
Z Han, Z Liang, F Yang, L Liu, L Li… - Advances in …, 2022 - proceedings.neurips.cc
Subpopulation shift widely exists in many real-world machine learning applications, referring to the training and test distributions containing the same subpopulation groups but varying in …
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 …
Evaluating the performance of machine learning models on diverse and underrepresented subgroups is essential for ensuring fairness and reliability in real-world applications …
C Zhou, X Ma, P Michel… - … Conference on Machine …, 2021 - proceedings.mlr.press
A central goal of machine learning is to learn robust representations that capture the fundamental relationship between inputs and output labels. However, minimizing training …
W Liang, J Zou - arXiv preprint arXiv:2202.06523, 2022 - arxiv.org
Understanding the performance of machine learning models across diverse data distributions is critically important for reliable applications. Motivated by this, there is a …
K Goel, A Gu, Y Li, C Ré - arXiv preprint arXiv:2008.06775, 2020 - arxiv.org
Classifiers in machine learning are often brittle when deployed. Particularly concerning are models with inconsistent performance on specific subgroups of a class, eg, exhibiting …
M Qraitem, K Saenko… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Prior work has shown that Visual Recognition datasets frequently underrepresent bias groups B (eg Female) within class labels Y (eg Programmers). This dataset bias can lead to …
Overparameterized neural networks can be highly accurate on average on an iid test set yet consistently fail on atypical groups of the data (eg, by learning spurious correlations that …