重新审视表格数据深度回归：目标函数与全局早停的局限性
Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping
AI总结：
本研究系统重新评估表格数据深度回归的目标函数，发现分位数损失表现更优，且全局早停因不确定性区域最优停止时间不同存在局限，提出异方差感知分位数损失扩展方案。
摘要：
尽管针对表格数据的深度学习模型近来受到了大量研究关注，但回归任务的目标函数选择仍是一个未被充分研究的自由度。多条研究路线提供了替代标准均方误差（MSE）的方案，但数据集、骨干网络和评估协议的差异使得它们的实际收益难以比较。在本研究中，我们通过在大量已建立的表格数据集和多个神经骨干网络上对回归目标函数进行系统的重新评估，来解决这一差距。我们的比较显示，许多提出的目标函数相较于经过适当调优的MSE基准，仅能提供有限或不一致的收益，而分位数损失在所有测试的骨干网络上均相较于MSE取得了一致的总体提升。随后，我们确定了一个即使使用这种强目标函数仍存在的局限性：具有不同目标噪声水平的区域会在不同的训练轮次达到其最佳预测性能。因此，单一的全局早停检查点会在不确定性区域之间做出妥协，即使目标函数能够表征异方差目标分布。受此局限性的启发，我们引入了分位数损失的异方差感知扩展，该扩展使用依赖输入的标签平滑作为潜在的补救措施，并在多个骨干网络上相较于分位数损失有所提升。总体而言，我们的结果提供了表格数据深度学习回归目标函数的现代实证图景，并强调了不确定性区域间最优停止时间的差异如何限制全局早停的有效性。代码可在该https URL获取。
英文摘要：
While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied degree of freedom. Several lines of research offer alternatives to the standard Mean Squared Error (MSE), but differences in datasets, backbones, and evaluation protocols make their practical benefits difficult to compare. In this work, we address this gap by performing a systematic re-evaluation of regression objectives across a broad collection of established tabular datasets and multiple neural backbones. Our comparison reveals that many proposed objectives provide limited or inconsistent gains over a properly tuned MSE baseline, while quantile loss yields consistent aggregate improvements over MSE across the tested backbones. We then identify a limitation that remains even with this strong objective: regions with different levels of target noise can reach their best predictive performance at different training epochs. Consequently, a single global early-stopping checkpoint can impose a compromise between uncertainty regions, even when the objective can represent heteroskedastic target distributions. Motivated by this limitation, we introduce a heteroskedasticity-aware extension of quantile loss that uses input-dependent label smoothing as a potential remedy and improves over quantile loss on several backbones. Overall, our results provide a modern empirical picture of regression objectives for tabular deep learning and highlight how differences in optimal stopping times across uncertainty regions can limit the effectiveness of global early stopping. The code is available at https://github.com/yandex-research/tabular-regression.
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。
