Domain Generalization Under Posterior Drift

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhu, Yilun, Deng, Naihao, Shi, Naichen, Gangrade, Aditya, Scott, Clayton
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910011404320768
author Zhu, Yilun
Deng, Naihao
Shi, Naichen
Gangrade, Aditya
Scott, Clayton
author_facet Zhu, Yilun
Deng, Naihao
Shi, Naichen
Gangrade, Aditya
Scott, Clayton
contents Domain generalization (DG) is the problem of generalizing from several distributions (or domains), for which labeled training data are available, to a new test domain for which no labeled data is available. For the prevailing benchmark datasets in DG, there exists a single classifier that performs well across all domains. In this work, we study a fundamentally different regime where the domains satisfy a \emph{posterior drift} assumption, in which the optimal classifier might vary substantially with domain. We establish a decision-theoretic framework for DG under posterior drift, and investigate the practical implications of this framework through experiments on language and vision tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04441
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Domain Generalization Under Posterior Drift
Zhu, Yilun
Deng, Naihao
Shi, Naichen
Gangrade, Aditya
Scott, Clayton
Machine Learning
Domain generalization (DG) is the problem of generalizing from several distributions (or domains), for which labeled training data are available, to a new test domain for which no labeled data is available. For the prevailing benchmark datasets in DG, there exists a single classifier that performs well across all domains. In this work, we study a fundamentally different regime where the domains satisfy a \emph{posterior drift} assumption, in which the optimal classifier might vary substantially with domain. We establish a decision-theoretic framework for DG under posterior drift, and investigate the practical implications of this framework through experiments on language and vision tasks.
title Domain Generalization Under Posterior Drift
topic Machine Learning
url https://arxiv.org/abs/2510.04441