Hikaru Ibayashi, Taufeq Mohammed Razakh, Liqiu Yang, Thomas M Linker, M. Olguin, Shinnosuke Hattori, Ye Luo, R. Kalia, A. Nakano, K. Nomura, P. Vashishta
{"title":"快板连奏: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","authors":"Hikaru Ibayashi, Taufeq Mohammed Razakh, Liqiu Yang, Thomas M Linker, M. Olguin, Shinnosuke Hattori, Ye Luo, R. Kalia, A. Nakano, K. Nomura, P. Vashishta","doi":"10.48550/arXiv.2303.08169","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":92039,"journal":{"name":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Allegro-Legato: Scalable, Fast, and Robust Neural-Network Quantum Molecular Dynamics via Sharpness-Aware Minimization\",\"authors\":\"Hikaru Ibayashi, Taufeq Mohammed Razakh, Liqiu Yang, Thomas M Linker, M. Olguin, Shinnosuke Hattori, Ye Luo, R. Kalia, A. Nakano, K. Nomura, P. Vashishta\",\"doi\":\"10.48550/arXiv.2303.08169\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"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.\",\"PeriodicalId\":92039,\"journal\":{\"name\":\"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-03-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2303.08169\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2303.08169","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Allegro-Legato: Scalable, Fast, and Robust Neural-Network Quantum Molecular Dynamics via Sharpness-Aware Minimization
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.