arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.16015cs.LGcs.DS
收藏

平稳校准的重要性

The Importance of Being Smoothly Calibrated

Apple(苹果公司);UT Austin(得克萨斯大学奥斯汀分校);Harvard(哈佛大学)

Parikshit Gopalan, Konstantinos Stavropoulos, Kunal Talwar, Pranay Tankala

AI总结:

本文探讨了平稳校准在鲁棒性校准误差中的核心作用,提出新的平稳预测保证,统一并扩展了以往基于平稳校准的预测结果,同时揭示了校准距离与地球移动距离的关系。

摘要:

近期研究强调了平稳校准[Kakade和Foster, 2008]作为稳健校准误差度量的核心地位。本文扩展、统一并扩展了平稳校准的先前结果,既作为稳健校准度量,又作为迈向全面预测的一步,使下游决策者在优化某些已知损失时能获得低遗憾的预测。我们为所有有界适当损失的预测器提出了新的全面预测保证。通过向预测器添加噪声,我们与任何基准预测器的平滑版本在空间上竞争,其中我们对预测器添加噪声后任意后处理。全面预测误差由预测器的平稳校准误差和基准的地球移动距离界定。我们展示了这种依赖性一般无法改进。我们展示了如何统一并扩展先前基于平稳校准的全面预测结果[Foster和Vohra, 1998; Hartline, Wu和Yang, 2025]。我们以预测与标签的最接近完美校准联合分布的地球移动距离来清晰地表征平稳校准。这还给出了与[Blasiok, Gopalan, Hu和Nakkiran, 2023]中校准下距离关系的更简单证明。我们利用这一点,证明了校准距离的上距离无法在与预测支持大小无关的样本复杂度内以二次因子估计。这与校准距离不同,后者的问题已知在信息理论上是不可能的:有限数量的样本不足以解决[Blasiok, Gopalan, Hu和Nakkiran, 2023]。

英文摘要:

Recent work has highlighted the centrality of smooth calibration [Kakade and Foster, 2008] as a robust measure of calibration error. We generalize, unify, and extend previous results on smooth calibration, both as a robust calibration measure, and as a step towards omniprediction, which enables predictions with low regret for downstream decision makers seeking to optimize some proper loss unknown to the predictor. We present a new omniprediction guarantee for smoothly calibrated predictors, for the class of all bounded proper losses. We smooth the predictor by adding some noise to it, and compete against smoothed versions of any benchmark predictor on the space, where we add some noise to the predictor and then post-process it arbitrarily. The omniprediction error is bounded by the smooth calibration error of the predictor and the earth mover's distance from the benchmark. We exhibit instances showing that this dependence cannot, in general, be improved. We show how this unifies and extends prior results [Foster and Vohra, 1998; Hartline, Wu, and Yang, 2025] on omniprediction from smooth calibration. We present a crisp new characterization of smooth calibration in terms of the earth mover's distance to the closest perfectly calibrated joint distribution of predictions and labels. This also yields a simpler proof of the relation to the lower distance to calibration from [Blasiok, Gopalan, Hu, and Nakkiran, 2023]. We use this to show that the upper distance to calibration cannot be estimated within a quadratic factor with sample complexity independent of the support size of the predictions. This is in contrast to the distance to calibration, where the corresponding problem was known to be information-theoretically impossible: no finite number of samples suffice [Blasiok, Gopalan, Hu, and Nakkiran, 2023].

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。

↑