A probabilistic framework for online test-time adaptation
Machine Learning
2026-06-24 v1 Machine Learning
Abstract
This paper presents a probabilistic framework for online test-time adaptation problems. In them, a model is trained on labeled data but must adapt to unlabeled data at test time under the assumption that training and test distributions potentially differ, that is, there might have been a distributional shift. The framework is based on a state-space modelling architecture from which parameter learning, parameter time evolution, prior tuning, and prediction can be characterized.
Cite
@article{arxiv.2606.26457,
title = {A probabilistic framework for online test-time adaptation},
author = {Daniel Corrales and David Ríos Insua},
journal= {arXiv preprint arXiv:2606.26457},
year = {2026}
}