研究人员推出了一种名为预测驱动的主动测试（PPAT）的新框架，旨在提高风险估计中的标签效率。PPAT集成了无偏的LURE估计器和预测驱动的控制变量，利用黑盒模型的预测来减少方差而不引入偏差。该框架还修改了点获取策略以进一步降低方差，并提供渐近有效的置信区间，在表格回归和图像分类任务上，与现有方法相比，在风险估计和覆盖率方面表现更优，且所需的标签更少。 AI
影响 通过利用黑盒模型的预测，提高了AI模型评估和风险估计的效率。
排序理由 该集群包含一篇在arXiv上发表的研究论文，详细介绍了一种用于AI模型测试的新统计方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Active testing provides a label--efficient approach to risk estimation by adaptively selecting which test points should be labelled. However, existing estimators fail to exploit the informative predictions of powerful black--box models, even though such predictions are increasing…
arXiv:2607.08347v1 Announce Type: new Abstract: Active testing provides a label--efficient approach to risk estimation by adaptively selecting which test points should be labelled. However, existing estimators fail to exploit the informative predictions of powerful black--box mod…
Active testing provides a label--efficient approach to risk estimation by adaptively selecting which test points should be labelled. However, existing estimators fail to exploit the informative predictions of powerful black--box models, even though such predictions are increasing…