arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.06714physics.chem-phphysics.comp-ph
收藏

机器学习量子化学的计算成本

Machine learning the computational cost of quantum chemistry

Stefan Heinen, Max Schwilk, Guido Falk von Rudorff, O. Anatole von Lilienfeld

摘要:

基于计算量子力学的分子和材料设计活动消耗越来越多的高性能计算资源,使得改进的作业调度效率是期望的,以便减少碳足迹或浪费性支出。我们介绍了量子机器学习(QML)模型的计算成本的常见量子化学任务。对于2D非线性玩具系统、单点、几何优化和过渡态计算,壁时间的QML模型的样本外预测误差随着训练集大小系统地衰减。我们提出了一个玩具系统,包含两个功能和三个常用的优化和数以千计的有机分子系统,包括封闭和开放的壳层平衡结构,以及过渡态的数值证据。考虑的电子结构理论水平包括B3 LYP/def 2-TZVP、MP2/6- 311 G(d)、局域CCSD(T)/VTZ-F12、CASSCF/VDZ-F12和MRCISD+Q-F12/VDZ-F12。与传统的无差别作业处理相比,基于QML的壁时间预测在仅对数千个分子进行训练后显著提高了所有任务的作业调度效率。由此产生的CPU时间开销减少了10%到90%。

英文摘要:

Computational quantum mechanics based molecular and materials design campaigns consume increasingly more high-performance compute resources, making improved job scheduling efficiency desirable in order to reduce carbon footprint or wasteful spending. We introduce quantum machine learning (QML) models of the computational cost of common quantum chemistry tasks. For 2D non-linear toy systems, single point, geometry optimization, and transition state calculations the out of sample prediction error of QML models of wall times decays systematically with training set size. We present numerical evidence for a toy system containing two functions and three commonly used optimizer and for thousands of organic molecular systems including closed and open shell equilibrium structures, as well as transition states. Levels of electronic structure theory considered include B3LYP/def2-TZVP, MP2/6-311G(d), local CCSD(T)/VTZ-F12, CASSCF/VDZ-F12, and MRCISD+Q-F12/VDZ-F12. In comparison to conventional indiscriminate job treatment, QML based wall time predictions significantly improve job scheduling efficiency for all tasks after training on just thousands of molecules. Resulting reductions in CPU time overhead range from 10% to 90%.

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。

↑