|国家预印本平台
首页|Representing spherical tensors with scalar-based machine-learning models

Representing spherical tensors with scalar-based machine-learning models

Representing spherical tensors with scalar-based machine-learning models

来源:Arxiv_logoArxiv
英文摘要

Rotational symmetry plays a central role in physics, providing an elegant framework to describe how the properties of 3D objects -- from atoms to the macroscopic scale -- transform under the action of rigid rotations. Equivariant models of 3D point clouds are able to approximate structure-property relations in a way that is fully consistent with the structure of the rotation group, by combining intermediate representations that are themselves spherical tensors. The symmetry constraints however make this approach computationally demanding and cumbersome to implement, which motivates increasingly popular unconstrained architectures that learn approximate symmetries as part of the training process. In this work, we explore a third route to tackle this learning problem, where equivariant functions are expressed as the product of a scalar function of the point cloud coordinates and a small basis of tensors with the appropriate symmetry. We also propose approximations of the general expressions that, while lacking universal approximation properties, are fast, simple to implement, and accurate in practical settings.

Michelangelo Domina、Filippo Bigi、Paolo Pegolo、Michele Ceriotti

物理学

Michelangelo Domina,Filippo Bigi,Paolo Pegolo,Michele Ceriotti.Representing spherical tensors with scalar-based machine-learning models[EB/OL].(2025-05-08)[2025-06-18].https://arxiv.org/abs/2505.05404.点此复制

评论