论文标题
无监督域适应的信息理论分析
Information-Theoretic Analysis of Unsupervised Domain Adaptation
论文作者
论文摘要
本文使用信息理论工具来分析无监督域适应（UDA）中的概括误差。我们为两个概括误差概念提出了新颖的上限。第一个概念衡量了目标域中的人口风险与源域中的差距，第二个概念衡量了目标域中的人口风险与源域中的经验风险之间的差距。尽管我们对第一种错误的界限符合传统分析并提供类似的见解，但我们对第二种错误的界限是算法依赖性的，这也提供了对算法设计的见解。具体而言，我们提出了两种简单的技术，用于改善UDA的概括并通过实验验证它们。
This paper uses information-theoretic tools to analyze the generalization error in unsupervised domain adaptation (UDA). We present novel upper bounds for two notions of generalization errors. The first notion measures the gap between the population risk in the target domain and that in the source domain, and the second measures the gap between the population risk in the target domain and the empirical risk in the source domain. While our bounds for the first kind of error are in line with the traditional analysis and give similar insights, our bounds on the second kind of error are algorithm-dependent, which also provide insights into algorithm designs. Specifically, we present two simple techniques for improving generalization in UDA and validate them experimentally.
