There has been enormous progress in the last few years in designing neural networks that respect the fundamental symmetries and coordinate freedoms of physical law. Some of these frameworks make use of irreducible representations, some make use of high-order tensor objects, and some apply symmetry-enforcing constraints. Different physical laws obey different combinations of fundamental symmetries, but a large fraction (possibly all) of classical physics is equivariant to translation, rotation, reflection (parity), boost (relativity), and permutations. Here we show that it is simple to parameterize universally approximating polynomial functions that are equivariant under these symmetries, or under the Euclidean, Lorentz, and Poincar\'e groups, at any dimensionality $d$. The key observation is that nonlinear O($d$)-equivariant (and related-group-equivariant) functions can be universally expressed in terms of a lightweight collection of scalars -- scalar products and scalar contractions of the scalar, vector, and tensor inputs. We complement our theory with numerical examples that show that the scalar-based method is simple, efficient, and scalable.
翻译:过去几年来,在设计尊重基本对称性和协调物理法自由的神经网络方面取得了巨大的进展,其中一些框架使用不可降低的表示法,有些框架使用高阶高压对象,有些则使用对称性约束。不同的物理法则在任何维度上遵守基本对称性的不同组合,但大部分(可能全部)古典物理(可能全部)对翻译、轮换、反射(平衡)、振动(相对性)和变异性(相对性)功能不一视同仁。在这里,我们表明,在这种对称性下或Euclidean、Lorentz和Poincar\e群下,对普遍近似多边功能的表示法比较简单,在这种对称性下或根据Euclidean、Lorentz和Poincar\'e群下,对准等式的表示法,非线性O(美元)-等式(和相关群体-等性)功能可以普遍以较轻的集合形式表示,对准性多式的多式多式混合功能是非等式的,对准性产品进行参数,对准性产品进行调节,对准性产品进行调节,对准性分析,对等式的理论,对准性理论,对等式的变压式的变制式的计算,对准性理论,对等式的变制式的变制式的变制式的变制式的变制式的变制式,对制式和制式的变制式的变制式,对制式的变制式的变制式,对制式,对制式的变制式的变制式,对制式,对制式的变制式,对制式的变制式的变制式的变制式,对制式和变制式的变制式的变制式,对制式的变制式,对制式,对制式,对制式,对制式的变制式的变制式的变制式的变制式的变制式的变制式的变制式的变制式的变制式的变制式,对制式的变制式的变制式的变制式的变制式的变制式的变制式的变制式的变制式的变制式