Saved in:
Bibliographic Details
Main Authors: Wang, Ziqiao, Mao, Yongyi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.01887
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912088921735168
author Wang, Ziqiao
Mao, Yongyi
author_facet Wang, Ziqiao
Mao, Yongyi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_01887
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On $f$-Divergence Principled Domain Adaptation: An Improved Framework
Wang, Ziqiao
Mao, Yongyi
Machine Learning
Computer Vision and Pattern Recognition
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.
title On $f$-Divergence Principled Domain Adaptation: An Improved Framework
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.01887