Machine-learned interatomic potentials (MLIPs) are increasingly used to replace computationally demanding electronic-structure calculations to model matter at the atomic scale. The most commonly used model architectures are constrained to fulfill a number of physical laws exactly, from geometric symmetries to energy conservation. Evidence is mounting that relaxing some of these constraints can be beneficial to the efficiency and (somewhat surprisingly) accuracy of MLIPs, even though care should be taken to avoid qualitative failures associated with the breaking of physical symmetries. Given the recent trend of scaling up models to larger numbers of parameters and training samples, a very important question is how unconstrained MLIPs behave in this limit. Here we investigate this issue, showing that -- when trained on large datasets -- unconstrained models can be superior in accuracy and speed when compared to physically constrained models. We assess these models both in terms of benchmark accuracy and in terms of usability in practical scenarios, focusing on static simulation workflows such as geometry optimization and lattice dynamics. We conclude that accurate unconstrained models can be applied with confidence, especially since simple inference-time modifications can be used to recover observables that are consistent with the relevant physical symmetries.

翻译：机器学习原子间势（MLIPs）正日益被用于替代计算成本高昂的电子结构计算，以在原子尺度上模拟物质。最常用的模型架构被约束为精确满足若干物理定律，从几何对称性到能量守恒。越来越多的证据表明，放宽其中一些约束有利于提高MLIPs的效率以及（某种程度上令人惊讶地）准确性，尽管需要注意避免因破坏物理对称性而导致的定性失效。鉴于近期模型向更大参数规模和训练样本量扩展的趋势，一个非常重要的问题是无约束MLIPs在此极限下的行为。本文对此展开研究，表明——当在大规模数据集上训练时——无约束模型在精度和速度上均可优于受物理约束的模型。我们从基准精度和实际场景可用性两个维度评估这些模型，重点关注几何优化和晶格动力学等静态模拟工作流。我们得出结论：准确的无约束模型可被可靠应用，尤其因为可通过简单的推理时修正来恢复与相关物理对称性一致的观测量。