当分布偏移发生时——混杂因素是罪魁祸首
When Shift Happens - Confounding Is to Blame
AI总结：
研究指出分布偏移下ERM表现优异及全协变量利用提升OOD泛化的现象源于隐藏混杂，证明需学习环境特定关系并可用代理变量缓解挑战，为OOD算法设计提供新指导。
摘要：
分布偏移引入了不确定性，削弱了机器学习模型的鲁棒性和泛化能力。传统观点认为，学习因果不变表示可以增强对此类偏移的鲁棒性，但最近的实证研究提出了一个反直觉的发现：(i) 经验风险最小化（ERM）可以匹敌甚至超越最先进的分布外（OOD）泛化方法，(ii) 当利用所有可用协变量而不仅是因果变量时，其OOD泛化性能会提升。基于实证和理论证据，我们将这一现象归因于隐藏混杂。隐藏混杂的偏移导致数据分布发生变化，违反了现有OOD泛化方法常作的假设。在此条件下，我们证明有效的泛化需要学习环境特定的关系，而非仅依赖不变关系。此外，我们表明，用隐藏混杂因素的代理变量增强的模型可以缓解隐藏混杂偏移带来的挑战。这些发现为设计鲁棒的OOD泛化算法和原则性协变量选择策略提供了新的理论洞见和实践指导。
英文摘要：
Distribution shifts introduce uncertainty that undermines the robustness and generalization capabilities of machine learning models. While conventional wisdom suggests that learning causal-invariant representations enhances robustness to such shifts, recent empirical studies present a counterintuitive finding: (i) empirical risk minimization (ERM) can rival or even outperform state-of-the-art out-of-distribution (OOD) generalization methods, and (ii) its OOD generalization performance improves when all available covariates, not just causal ones, are utilized. Drawing on both empirical and theoretical evidence, we attribute this phenomenon to hidden confounding. Shifts in hidden confounding induce changes in data distributions that violate assumptions commonly made by existing OOD generalization approaches. Under such conditions, we prove that effective generalization requires learning environment-specific relationships, rather than relying solely on invariant ones. Furthermore, we show that models augmented with proxies for hidden confounders can mitigate the challenges posed by hidden confounding shifts. These findings offer new theoretical insights and practical guidance for designing robust OOD generalization algorithms and principled covariate selection strategies.
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。
