arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.05261stat.MLcond-mat.mtrl-scics.LG
收藏

表示与学习在晶体群下不变的函数

Representing and Learning Functions Invariant Under Crystallographic Groups

Ryan P. Adams, Peter Orbanz

AI总结:

本文研究晶体群下光滑不变函数的表示与学习,提出推广 Fourier 基的线性表示和基于 orbifold 的有限维非线性嵌入,并给出计算算法及不变神经网络、核机器与 Gaussian 过程示例。

摘要:

晶体群描述了晶体以及自然界和科学中遇到的其他重复性结构的对称性。这些群包括壁纸群和空间群。我们推导了同时满足(1)光滑且(2)在此类群下不变的函数的线性与非线性表示。线性表示将 Fourier 基推广为晶体不变基函数。我们证明了每个晶体群都存在这样一个基,它在相应的 $L_2$ 空间中是正交归一的,并且在纯平移群这一特殊情形下恢复为标准 Fourier 基。非线性表示将群的轨道空间嵌入到一个有限维 Euclidean 空间中。我们证明了每个晶体群都存在这样的嵌入,并且它通过一种称为 orbifold(轨形)的流形推广来分解函数。我们描述了若干算法:在给定群的标准化描述时,计算 Fourier 基和嵌入映射。作为示例,我们构建了晶体不变神经网络、核机器和 Gaussian 过程。

英文摘要:

Crystallographic groups describe the symmetries of crystals and other repetitive structures encountered in nature and the sciences. These groups include the wallpaper and space groups. We derive linear and nonlinear representations of functions that are (1) smooth and (2) invariant under such a group. The linear representation generalizes the Fourier basis to crystallographically invariant basis functions. We show that such a basis exists for each crystallographic group, that it is orthonormal in the relevant $L_2$ space, and recover the standard Fourier basis as a special case for pure shift groups. The nonlinear representation embeds the orbit space of the group into a finite-dimensional Euclidean space. We show that such an embedding exists for every crystallographic group, and that it factors functions through a generalization of a manifold called an orbifold. We describe algorithms that, given a standardized description of the group, compute the Fourier basis and an embedding map. As examples, we construct crystallographically invariant neural networks, kernel machines, and Gaussian processes.

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。

↑