论文标题
关于域适应的本地化差异
On Localized Discrepancy for Domain Adaptation
论文作者
论文摘要
我们提出了基于无监督的域适应性的基于群体的泛化理论。以前的理论引入了分布差异，定义为完整假设空间的至上。假设空间可能包含导致风险结合的不必要高估的假设。本文研究了定位后的假设空间上定义的局部差异。首先，我们表明这些差异具有理想的属性。它们可能比透明的差异要小得多。如果我们交换两个域，它们的值将有所不同，因此可以揭示不对称的转移困难。接下来，我们通过这些差异得出了改善的概括界限。我们表明，差异可能会影响样本复杂性的速率。最后，我们进一步扩展了局部差异，以实现超级传递和得出概括范围，这些范围可能对源域上的样本效率更高。
We propose the discrepancy-based generalization theories for unsupervised domain adaptation. Previous theories introduced distribution discrepancies defined as the supremum over complete hypothesis space. The hypothesis space may contain hypotheses that lead to unnecessary overestimation of the risk bound. This paper studies the localized discrepancies defined on the hypothesis space after localization. First, we show that these discrepancies have desirable properties. They could be significantly smaller than the pervious discrepancies. Their values will be different if we exchange the two domains, thus can reveal asymmetric transfer difficulties. Next, we derive improved generalization bounds with these discrepancies. We show that the discrepancies could influence the rate of the sample complexity. Finally, we further extend the localized discrepancies for achieving super transfer and derive generalization bounds that could be even more sample-efficient on source domain.
