English(EN) Benchmarking uncertainty quantification for engineering regression under graded distribution shift

新基准评估AI在分布变化下的不确定性量化

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

一篇新论文介绍了一种新颖的三级变化梯子，用于评估工程回归任务中的不确定性量化，超越了随机数据划分。该研究在七个公开的工程数据集上测试了12种方法，模拟了分布内、软变化和硬变化条件。结果表明，虽然一致性方法在分布内表现良好，但其在硬变化下的有效性会显著下降，没有一种明确的方法优于其他方法。研究还发现，源验证增益并不能可靠地预测硬变化条件下的改进，这表明在实际工程应用中需要更鲁棒的评估策略。 AI

影响强调了当前AI不确定性量化方法在实际工程应用中的局限性，并提出了改进评估和弃权策略的必要性。

排序理由关于AI方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于AI方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Ahmad Lawal, Rahim Pasbanigoloojeh, Asmau Lawal Bilbis · 2026-10-28 04:00

工程回归在分级分布变化下的不确定性量化基准测试

arXiv:2610.35356v1 Announce Type: new Abstract: Machine learning models in engineering are often used beyond their training conditions, where reliable uncertainty quantification (UQ) matters most. Existing comparisons of regression UQ methods rely on random splits, which assess c…

本文如何被排名

报道来源 [1]

工程回归在分级分布变化下的不确定性量化基准测试

相关实体

相关话题