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 by 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 yields 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). Leveraging a localization technique, we also develop a fast-rate
generalization bound. Empirical results demonstrate the superior performance of
f-DD-based domain learning algorithms over previous works in popular UDA
benchmarks.

我们改进了 Acuna 等人提出的无监督领域自适应（UDA）的理论基础，通过改进他们基于 f - 差异度的不一致性，并引入一个新的度量，即 f - 域差异度（f-DD）。通过去除绝对值函数并结合一个缩放参数，f-DD 产生了新的目标误差和样本复杂度界限，使我们能够恢复先前基于 KL 的结果，并弥合了 Acuna 等人（2021）提出的算法与理论之间的差距。利用一种定位技术，我们还开发了一个快速学习界限。实证结果表明，在流行的 UDA 基准测试中，基于 f-DD 的领域学习算法比以前的工作表现更优秀。