Out-of-distribution (OOD) generalization remains challenging when models simultaneously encounter correlation shifts across environments and diversity shifts driven by rare or hard samples. Existing invariant risk minimization (IRM) methods primarily address spurious correlations at the environment level, but often overlook sample-level heterogeneity within environments, which can critically impact OOD performance. In this work, we propose \emph{Environment-Conditioned Tail Reweighting for Total Variation Invariant Risk Minimization} (ECTR), a unified framework that augments TV-based invariant learning with environment-conditioned tail reweighting to jointly address both types of distribution shift. By integrating environment-level invariance with within-environment robustness, the proposed approach makes these two mechanisms complementary under mixed distribution shifts. We further extend the framework to scenarios without explicit environment annotations by inferring latent environments through a minimax formulation. Experiments across regression, tabular, time-series, and image classification benchmarks under mixed distribution shifts demonstrate consistent improvements in both worst-environment and average OOD performance.

翻译：当模型同时面临跨环境的相关性偏移以及由稀有或困难样本驱动的多样性偏移时，分布外泛化仍然具有挑战性。现有的不变风险最小化方法主要解决环境层面的虚假相关性，但常常忽略环境内部的样本级异质性，而这可能对分布外性能产生关键影响。在本工作中，我们提出了**环境条件尾部重加权用于全变差不变风险最小化**，这是一个统一框架，通过环境条件尾部重加权来增强基于全变差的不变学习，以共同应对这两种类型的分布偏移。通过将环境层面的不变性与环境内的鲁棒性相结合，所提出的方法使得这两种机制在混合分布偏移下互为补充。我们进一步将该框架扩展到没有显式环境标注的场景，通过极小极大公式推断潜在环境。在混合分布偏移下，跨回归、表格数据、时间序列和图像分类基准的实验表明，该方法在最差环境和平均分布外性能上均取得了持续改进。