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 2303.08169cs.DCcs.LGphysics.comp-ph
收藏

Allegro-Legato:通过锐度感知最小化的可扩展、快速和鲁棒的神经网络量子分子动力学

Allegro-Legato: Scalable, Fast, and Robust Neural-Network Quantum Molecular Dynamics via Sharpness-Aware Minimization

University of Southern California(南加州大学);Sony Group Corporation(索尼集团公司);Argonne National Laboratory(阿贡国家实验室)

Hikaru Ibayashi, Taufeq Mohammed Razakh, Liqiu Yang, Thomas Linker, Marco Olguin, Shinnosuke Hattori, Ye Luo, Rajiv K. Kalia, Aiichiro Nakano, Ken-ichi Nomura, Priya Vashishta

摘要:

基于机器学习的神经网络量子分子动力学(NNQMD)模拟通过提供量子力学精度但更快的数量级来彻底改变材料的原子模拟,ACM戈登贝尔奖(2020)和决赛选手(2021)说明了这一点。最先进的(SOTA)NNQMD模型建立在群论的基础上,具有旋转等方差和局部描述符,提供了比这些模型更高的准确性和速度,因此被命名为Allegro(意思是快速)。然而,在大规模并行超级计算机上,它遇到了一个量子尺度问题,即越来越多的原子间力的非物理预测禁止更长时间地模拟涉及大量原子的模拟。在这里,我们通过将Allegro模型与锐度感知最小化(SAM)相结合来解决这个问题,以通过改善损失景观的平滑度来增强模型的鲁棒性。由此产生的Allegro-Legato(意思是快速和“平滑”)模型被证明可以延长故障时间$t_\textrm{failure}$,而不会牺牲计算速度或精度。具体来说,与SOTA Allegro模型$\left(t_{\textrm{failure}} \propto N^{-0.29}\right)$相比,Allegro-Legato的故障时间对问题大小$t_{\textrm{failure}} \propto N^{-0.14}$($N$是原子数)的依赖性要弱得多,即,系统地延迟了故障时间,从而允许更大和更长的NNQMD模拟而不会失败。该模型还表现出出色的计算可扩展性和GPU加速的北极星超级计算机在阿贡领导计算设施。这种可扩展的,准确的,快速的和强大的NNQMD模型可能会发现广泛的应用在新兴的exaflop/s计算机上的NNQMD模拟,在氨动力学中的核量子效应的一个具体例子。

英文摘要:

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.

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。

↑