Neural-network quantum molecular dynamics (NNQMD) simulations based on machine learning are revolutionizing atomistic simulations of materials by providing quantum-mechanical accuracy but orders-of-magnitude faster, illustrated by ACM Gordon Bell prize (2020) and finalist (2021). State-of-the-art (SOTA) NNQMD model founded on group theory featuring rotational equivariance and local descriptors has provided much higher accuracy and speed than those models, thus named Allegro (meaning fast). On massively parallel supercomputers, however, it suffers a fidelity-scaling problem, where growing number of unphysical predictions of interatomic forces prohibits simulations involving larger numbers of atoms for longer times. Here, we solve this problem by combining the Allegro model with sharpness aware minimization (SAM) for enhancing the robustness of model through improved smoothness of the loss landscape. The resulting Allegro-Legato (meaning fast and "smooth") model was shown to elongate the time-to-failure $t_\textrm{failure}$, without sacrificing computational speed or accuracy. Specifically, Allegro-Legato exhibits much weaker dependence of timei-to-failure on the problem size, $t_{\textrm{failure}} \propto N^{-0.14}$ ($N$ is the number of atoms) compared to the SOTA Allegro model $\left(t_{\textrm{failure}} \propto N^{-0.29}\right)$, i.e., systematically delayed time-to-failure, thus allowing much larger and longer NNQMD simulations without failure. The model also exhibits excellent computational scalability and GPU acceleration on the Polaris supercomputer at Argonne Leadership Computing Facility. Such scalable, accurate, fast and robust NNQMD models will likely find broad applications in NNQMD simulations on emerging exaflop/s computers, with a specific example of accounting for nuclear quantum effects in the dynamics of ammonia.
翻译:以机器学习为基础的神经网络量子分子动态(NNQMD)模拟(NNQMD)正在通过提供量子机械性精度,而以ACM Gordon Bell奖(202020年)和终极主义者(2021年)为例证,使材料的原子模拟发生革命性变化。基于以旋转等离差和本地描述器为特点的集团理论,NNNQ-网络分子动态(NNNNQMMD)。因此,Allegro-Legro(意为快速),在大规模平行的超级计算机模拟中,它遇到了一个忠度加速的问题,而不断增长的对内部力量的不物理预测无法模拟涉及更多原子数量(202020年)和终极主义者(2021年)。在这里,我们通过将Allegro模型与敏锐度意识最小化(SAM)相结合,通过改善损失地平滑度,提高模型的坚固度。Allegro-Ideal-deal-modeal-modeal-modeal-moudal-moudal-modeal Qal-moudal-moudal-moudal QQQQQQQQQQQQQQQ), modeal-modeal-modal-modeal-modeal-moudal-modal-moudal-modal-mod-mod-modal-modaldal-modal-modal-modal-modaldald-mod-modal-modal-mod-mod-mod-mod-mod-mod-modal-mod-mod-modal-modal-mod-mod-mod-mod-mod-modal-modal-modal-modal-modal-modal-mod-modal-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-modal-mod-mod-mod-mod-mod-mo</s>