研究人员开发了一种新的诊断工具，用于评估回归任务伪标签流程中置信度阈值的可靠性。该方法利用未标记数据上的残差分数方差，预测阈值校准分类器分数引入的偏差。提出的 $(V^{*}, \kappa)$ 决策规则旨在帮助实践者确定何时置信度阈值是一种安全做法。 AI
影响 为实践者提供了一个新的操作工具，以提高伪标签回归模型的可靠性。
排序理由 该集群包含一篇学术论文，详细介绍了用于统计分析的新方法和诊断工具。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.12780v1 Announce Type: cross Abstract: Calibrated probability outputs of trained classifiers are increasingly used as inputs to downstream regression estimands such as effects, prevalences, or disparities for a latent group observed only on a small labelled subset. A s…
Calibrated probability outputs of trained classifiers are increasingly used as inputs to downstream regression estimands such as effects, prevalences, or disparities for a latent group observed only on a small labelled subset. A standard practice is to threshold the calibrated sc…