English(EN) Coordinate-Free Automatic Differentiation

新的无坐标自动微分算子将几何学融入机器学习

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-12 04:00

研究人员开发了一种新的、无坐标的自动微分（AD）算子，可以表示各种几何微分运算。该算子旨在与JAX等现有AD框架无缝集成，从而将旋转和曲率等数学对象融入机器学习应用。该系统已通过实验验证，证明其在不同流形算子上的可重用性以及在逆问题管道中的可组合性。 AI

影响使机器学习模型中的几何运算更加复杂，有可能改善AI在科学领域的应用。

排序理由学术论文，详细介绍了一种用于自动微分的新数学算子。[lever_c_demoted from research: ic=1 ai=1.0]

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; 学术论文，详细介绍了一种用于自动微分的新数学算子。[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: 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。

arXiv cs.LG TIER_1 English(EN) · Alex Guerra, Joshua Aduol, Yaqian Tang, Daniel Williams, Ryan P. Adams, Peter Orbanz · 2026-10-12 04:00

无坐标自动微分

arXiv:2610.12776v1 Announce Type: new Abstract: Automatic differentiation (AD) is a cornerstone of modern machine learning. Since all AD frameworks implicitly fix a basis of Euclidean space to define gradients and Jacobians, they natively process mathematical objects that are arr…