arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.01883stat.MLcs.LG
收藏

不变性在分布外推广问题中何时有用?

When is invariance useful in an Out-of-Distribution Generalization problem ?

Preferred Networks

Masanori Koyama, Shoichiro Yamaguchi

摘要:

分布外(OOD)泛化问题的目标是训练一个能在所有环境下泛化的预测器。该领域的流行方法使用这样的假设,即这种预测器应该是一个\textit{invariant predictor},它捕获在不同环境中保持恒定的机制。虽然这些方法在各种案例研究中取得了实验成功,但这一假设的理论验证仍有很大的空间。本文提出了一组新的理论条件所需的不变预测,以实现OOD最优性。我们的理论不仅适用于非线性情形,而且推广了\citet{rojas2018invariant}中的必要条件。我们还从我们的理论中推导出帧间梯度对齐算法,并在MNIST衍生的基准数据集上以及在\citet{aubinlinear}提出的三个\textit{Invariance Unit Tests}中的两个上证明了其竞争力。

英文摘要:

The goal of Out-of-Distribution (OOD) generalization problem is to train a predictor that generalizes on all environments. Popular approaches in this field use the hypothesis that such a predictor shall be an \textit{invariant predictor} that captures the mechanism that remains constant across environments. While these approaches have been experimentally successful in various case studies, there is still much room for the theoretical validation of this hypothesis. This paper presents a new set of theoretical conditions necessary for an invariant predictor to achieve the OOD optimality. Our theory not only applies to non-linear cases, but also generalizes the necessary condition used in \citet{rojas2018invariant}. We also derive Inter Gradient Alignment algorithm from our theory and demonstrate its competitiveness on MNIST-derived benchmark datasets as well as on two of the three \textit{Invariance Unit Tests} proposed by \citet{aubinlinear}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑