English(EN) Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency

新方法实现神经算子的即时导数信息训练

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

研究人员开发了一种名为草图切线一致性损失（sTCL）的新方法来训练神经算子。该技术允许即时进行导数信息训练，无需进行缓慢且存储密集型的离线导数标签。sTCL 使用随机草图输入扰动直接从控制方程强制执行灵敏度一致性，使其能够适应不同的数据集和分辨率。该方法在包括 Navier-Stokes 在内的各种方程上，展示了与现有离线方法相当的准确性，同时显著简化了训练过程。 AI

影响简化了神经算子的训练，有可能加速其在逆问题和控制系统中的应用。

排序理由学术论文，详细介绍了一种训练神经算子的新方法。[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: 34 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了一种训练神经算子的新方法。[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, infra; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Xinhan Yang, Lu Lu, Shancong Mou · 2026-11-11 05:00

通过草图切线一致性对神经网络算子进行导数信息在线训练

arXiv:2609.32797v2 Announce Type: replace Abstract: Derivative-informed training improves neural operators by directly supervising their input-output sensitivities, which is crucial when neural operators are used as differentiable surrogates for inverse problems, PDE-constrained …

本文如何被排名

报道来源 [1]

通过草图切线一致性对神经网络算子进行导数信息在线训练

相关实体

相关话题