arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.08758cs.LGcs.AI

柔性等变神经场的等变性缩减

Generalized Reduction to the Isotropy for Flexible Equivariant Neural Fields

Amsterdam Machine Learning Lab (AMLab), University of Amsterdam(阿姆斯特丹机器学习实验室(AMLab),阿姆斯特丹大学);Department of Mathematics and Computer Science, Eindhoven University of Technology(数学与计算机科学系,埃因霍温理工大学);Leiden Institute of Advanced Computer Science, Universiteit Leiden(莱顿高级计算机科学研究所,莱顿大学)

Alejandro García-Castellanos, Gijs Bellaard, Remco Duits, Daniel Pelt, Erik J Bekkers

AI总结:

本文提出了一种将柔性等变神经场的等变性缩减到等变子群作用的方法,扩展了神经场的适用范围并去除了现有方法的结构限制。

摘要:

许多几何学习问题需要对异质乘积空间上的不变量,即不同群作用的乘积空间,其中标准技术无法直接应用。我们证明,当群G在空间M上作用时,任何在乘积空间X×M上的G不变函数可以被缩减为M的等变子群H作用于X上的不变量。我们的方法建立了显式的轨道等价(X×M)/G ≅ X/H,从而产生一种保留表达力的缩减方法。我们将这一特征应用于等变神经场,将其扩展到任意群作用和同质条件空间,从而移除了现有方法主要结构约束。

英文摘要:

Many geometric learning problems require invariants on heterogeneous product spaces, i.e., products of distinct spaces carrying different group actions, where standard techniques do not directly apply. We show that, when a group $G$ acts transitively on a space $M$, any $G$-invariant function on a product space $X \times M$ can be reduced to an invariant of the isotropy subgroup $H$ of $M$ acting on $X$ alone. Our approach establishes an explicit orbit equivalence $(X \times M)/G \cong X/H$, yielding a principled reduction that preserves expressivity. We apply this characterization to Equivariant Neural Fields, extending them to arbitrary group actions and homogeneous conditioning spaces, and thereby removing the major structural constraints imposed by existing methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑