等变框架与连续规范化的不可能性
Equivariant Frames and the Impossibility of Continuous Canonicalization
AI总结:
该研究从理论上证明常用群下无加权框架平均无法保持函数连续性,定义并构建可证明保持连续性的加权框架,还针对点云的几类群作用实现了高效连续的加权框架,为概率框架的经验优势提供了理论支撑。
摘要:
规范化提供了一种与架构无关的等变性约束方法,诸如框架平均之类的推广形式作为等变架构的轻量灵活替代方案,近年来备受关注。近期研究通过经验发现,使用学习群元素上加权分布的概率框架更具优势。本研究为这一现象提供了有力的理论依据:对于常用群,不存在可高效计算、且能保持被平均函数连续性的框架选择。换言之,无加权框架平均可能将平滑的非对称函数转化为不连续的对称函数。为解决这一根本性鲁棒性问题,我们正式定义并构建了加权框架,其可证明能保持连续性;我们还针对点云上的$SO(2)$、$SO(3)$和$S_n$作用构建了高效连续的加权框架,验证了其实用性。
英文摘要:
Canonicalization provides an architecture-agnostic method for enforcing equivariance, with generalizations such as frame-averaging recently gaining prominence as a lightweight and flexible alternative to equivariant architectures. Recent works have found an empirical benefit to using probabilistic frames instead, which learn weighted distributions over group elements. In this work, we provide strong theoretical justification for this phenomenon: for commonly-used groups, there is no efficiently computable choice of frame that preserves continuity of the function being averaged. In other words, unweighted frame-averaging can turn a smooth, non-symmetric function into a discontinuous, symmetric function. To address this fundamental robustness problem, we formally define and construct \emph{weighted} frames, which provably preserve continuity, and demonstrate their utility by constructing efficient and continuous weighted frames for the actions of $SO(2)$, $SO(3)$, and $S_n$ on point clouds.
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。