On $f$-Divergence Principled Domain Adaptation: An Improved Framework

Ziqiao Wang; Yongyi Mao

NeurIPS 2024poster5 citations

On $f$-Divergence Principled Domain Adaptation: An Improved Framework

Abstract

Unsupervised domain adaptation (UDA) plays a crucial role in addressing distribution shifts in machine learning. In this work, we improve the theoretical foundations of UDA proposed in Acuna et al. (2021) by refining their $f$-divergence-based discrepancy and additionally introducing a new measure, $f$-domain discrepancy ($f$-DD). By removing the absolute value function and incorporating a scaling parameter, $f$-DD obtains novel target error and sample complexity bounds, allowing us to recover previous KL-based results and bridging the gap between algorithms and theory presented in Acuna et al. (2021). Using a localization technique, we also develop a fast-rate generalization bound. Empirical results demonstrate the superior performance of $f$-DD-based learning algorithms over previous works in popular UDA benchmarks.

learning theoryunsupervised domain adaptationf-divergencegeneralization

BibTeX

@inproceedings{
wang2024on,
title={On \$f\$-Divergence Principled Domain Adaptation: An Improved Framework},
author={Ziqiao Wang and Yongyi Mao},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=xSU27DgWEr}
}