Saved in:
Bibliographic Details
Main Authors: Jeong, Yujin, Rothenhäusler, Dominik
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.18370
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915140621828096
author Jeong, Yujin
Rothenhäusler, Dominik
author_facet Jeong, Yujin
Rothenhäusler, Dominik
contents Many existing approaches for estimating parameters in settings with distributional shifts operate under an invariance assumption. For example, under covariate shift, it is assumed that $p(y|x)$ remains invariant. We refer to such distribution shifts as sparse, since they may be substantial but affect only a part of the data generating system. In contrast, in various real-world settings, shifts might be dense. More specifically, these dense distributional shifts may arise through numerous small and random changes in the population and environment. First, we discuss empirical evidence for such random dense distributional shifts. Then, we develop tools to infer parameters and make predictions for partially observed, shifted distributions. Finally, we apply the framework to several real-world datasets and discuss diagnostics to evaluate the fit of the distributional uncertainty model.
format Preprint
id arxiv_https___arxiv_org_abs_2404_18370
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Out-of-distribution generalization under random, dense distributional shifts
Jeong, Yujin
Rothenhäusler, Dominik
Methodology
Many existing approaches for estimating parameters in settings with distributional shifts operate under an invariance assumption. For example, under covariate shift, it is assumed that $p(y|x)$ remains invariant. We refer to such distribution shifts as sparse, since they may be substantial but affect only a part of the data generating system. In contrast, in various real-world settings, shifts might be dense. More specifically, these dense distributional shifts may arise through numerous small and random changes in the population and environment. First, we discuss empirical evidence for such random dense distributional shifts. Then, we develop tools to infer parameters and make predictions for partially observed, shifted distributions. Finally, we apply the framework to several real-world datasets and discuss diagnostics to evaluate the fit of the distributional uncertainty model.
title Out-of-distribution generalization under random, dense distributional shifts
topic Methodology
url https://arxiv.org/abs/2404.18370