超越经验支持：通过Sinkhorn最优输运的结构化离群点生成
Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport
AI总结：
针对现有离群点合成方法依赖启发式且不稳定，本文提出Sinkhorn边界离群点生成（SBOG）框架，结合最优输运几何与分布鲁棒边界建模，生成语义受控的离群点，提升跨模态鲁棒性评估。
AI中文摘要：
离群点对于评估和提高机器学习系统的鲁棒性至关重要，尤其是在未来分布可能与历史训练数据显著不同的情况下。在高风险应用中，鲁棒性往往依赖于有限数据集无法捕获的罕见情况，这使得简单的重采样或扰动不足以生成压力场景。现有的离群点合成方法通常依赖于稀疏邻域、低支持潜在区域或分类器边界穿越，这些方法可能是启发式的、不稳定的，并且与特定模态或架构绑定。因此，我们提出了Sinkhorn边界离群点生成（SBOG），一种用于潜在空间离群点生成的结构化框架，它将Sinkhorn最优输运几何与分布鲁棒边界建模相结合。由此产生的Sinkhorn诱导支持成本引导采样器朝向弱支持的边界区域，而语义约束防止不受控制地偏离预期上下文，从而产生相对于分布内参考度量的受控偏差，而非任意稀疏区域样本。在时间序列异常生成和图像离群点合成上的实验表明，我们的框架能够生成信息丰富、语义受控的离群点，并改善跨模态的下游鲁棒性评估，为超越经验支持的压力场景生成提供了基础。
英文摘要：
Outliers are essential for evaluating and improving the robustness of machine learning systems, especially when future distributions may differ significantly from historical training data. In high-stakes applications, robustness often depends on rare cases that finite datasets fail to capture, making simple resampling or perturbation insufficient for stress scenario generation. Existing outlier synthesis methods typically rely on sparse neighborhoods, low support latent regions, or classifier boundary crossings, which can be heuristic, unstable, and tied to specific modalities or architectures. We therefore propose Sinkhorn Boundary Outlier Generation (SBOG), a structured framework for latent-space outlier generation that couples Sinkhorn optimal transport geometry with distributionally robust boundary modeling. The resulting Sinkhorn-induced support cost guides the sampler toward weakly supported boundary regions, while semantic constraints prevent uncontrolled drift from the intended context, yielding controlled deviations from the in-distribution reference measure rather than arbitrary sparse-region samples. Experiments on time series anomaly generation and image outlier synthesis show that our framework produces informative, semantically controlled outliers and improves downstream robustness evaluation across modalities, providing a foundation for stress scenario generation beyond empirical support.
