论文标题
风险差异惩罚
Risk Variance Penalization
论文作者
论文摘要
分布外（OOD）概括的关键是将训练域到目标域的不变性概括。差异风险外推（V-REX）是一种实用的OOD方法，取决于域级别的正则化，但缺乏对其动机和效用的理论验证。本文通过研究基于方差的正常化程序，提供了对V-Rex的理论见解。我们提出了风险差异惩罚（RVP），该风险差异稍微改变了V-Rex的正则化，但解决了对V-Rex的理论关注。我们为RVP的正则化参数提供了理论解释和理论启发的调整方案。我们的结果指出，RVP发现了一个强大的预测因子。最后，我们通过实验表明，在某些条件下，提出的正规器可以找到不变的预测因子。
The key of the out-of-distribution (OOD) generalization is to generalize invariance from training domains to target domains. The variance risk extrapolation (V-REx) is a practical OOD method, which depends on a domain-level regularization but lacks theoretical verifications about its motivation and utility. This article provides theoretical insights into V-REx by studying a variance-based regularizer. We propose Risk Variance Penalization (RVP), which slightly changes the regularization of V-REx but addresses the theory concerns about V-REx. We provide theoretical explanations and a theory-inspired tuning scheme for the regularization parameter of RVP. Our results point out that RVP discovers a robust predictor. Finally, we experimentally show that the proposed regularizer can find an invariant predictor under certain conditions.
