研究人员引入了一个新颖的后验“学习推迟”（L2D）框架，该框架通过理想分布的视角重塑了该问题。该方法通过计算模型和专家理想分布之间的密度比来定义推迟。导出的 DR CPE 损失允许在无需重新训练的情况下调整推迟率，实验结果表明在各种数据集上具有竞争力的性能和鲁棒性。 AI
影响 为模型推迟引入了新的理论框架，有望提高系统的可靠性和可解释性。
排序理由 该集群包含一篇详细介绍新机器学习方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
新框架通过密度比估计重塑“学习推迟”问题
报道来源 [2]
-
Density-Ratio Losses for Post-Hoc Learning to Defer
arXiv:2605.19557v1 Announce Type: new Abstract: We study post-hoc Learning to Defer (L2D) through the lens of ideal distributions: divergence-regularized reweightings of the data distribution under which a model attains low loss. We define deferral via the density-ratio between a…
-
Density-Ratio Losses for Post-Hoc Learning to Defer
We study post-hoc Learning to Defer (L2D) through the lens of ideal distributions: divergence-regularized reweightings of the data distribution under which a model attains low loss. We define deferral via the density-ratio between a model's and an expert's ideals. Using the reduc…