一篇新发表在arXiv上的研究论文探讨了重采样方法对树集成模型概率校准能力的影响。研究发现，虽然SMOTE（合成少数类过采样技术）会导致校准能力轻微下降，但随机欠采样会带来重大风险，尤其是在高不平衡比率下，它会扭曲训练数据，使概率估计不可靠。幸运的是，像Platt或等渗缩放这样的事后重新校准技术可以有效消除这种校准损害，同时对判别性能的影响极小。 AI
影响 强调了在不平衡数据集上概率校准能力的重要性，并为实践者提供了实用的解决方案。
排序理由 该集群包含一篇详细介绍机器学习模型校准能力研究结果的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.29720v1 Announce Type: cross Abstract: Resampling methods such as SMOTE and random under/over-sampling are standard tools for class-imbalanced classification, almost always evaluated by minority-class accuracy or F1. Prior work has established that undersampling degrad…
Resampling methods such as SMOTE and random under/over-sampling are standard tools for class-imbalanced classification, almost always evaluated by minority-class accuracy or F1. Prior work has established that undersampling degrades probability calibration by distorting the train…