论文标题

关于通用域概括方法的局限性

On the Limitations of General Purpose Domain Generalisation Methods

论文作者

Gouk, Henry, Bohdal, Ondrej, Li, Da, Hospedales, Timothy

论文摘要

我们研究了几个领域概括(DG)设置中学习算法的基本性能局限性。以先前提出的方法可靠地优于经验风险最小化(ERM)的难度,我们在ERM的多余风险方面得出了上限,以及最小值多余的风险。我们的发现表明,在我们考虑的所有DG设置中,不可能显着胜过ERM。我们的结论不仅限于标准的协变量偏移设置,而且还限于其他两个设置,并且对域的不同差异有其他限制。第一个将所有域限制为在成对距离上具有非平凡绑定,这是通过一类广泛的积分概率指标来衡量的。第二个备用设置考虑了所有域都具有相同基础支持的限制类别的DG问题。我们的分析还表明,如何使用不同的策略来优化这些DG设置中ERM的性能。我们还通过实验探讨了通过我们的理论分析提出的假设。

We investigate the fundamental performance limitations of learning algorithms in several Domain Generalisation (DG) settings. Motivated by the difficulty with which previously proposed methods have in reliably outperforming Empirical Risk Minimisation (ERM), we derive upper bounds on the excess risk of ERM, and lower bounds on the minimax excess risk. Our findings show that in all the DG settings we consider, it is not possible to significantly outperform ERM. Our conclusions are limited not only to the standard covariate shift setting, but also two other settings with additional restrictions on how domains can differ. The first constrains all domains to have a non-trivial bound on pairwise distances, as measured by a broad class of integral probability metrics. The second alternate setting considers a restricted class of DG problems where all domains have the same underlying support. Our analysis also suggests how different strategies can be used to optimise the performance of ERM in each of these DG setting. We also experimentally explore hypotheses suggested by our theoretical analysis.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源