通过机器学习进行量子力学模拟插值的分子和材料表示
Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
摘要:
从第一性原理出发对分子和材料进行计算研究是物理学、化学和材料科学的基石,但受到精确和精确模拟成本的限制。在涉及许多模拟的设置中,机器学习可以通过在参考模拟之间进行插值来降低这些成本,通常是数量级的。这需要描述任何分子或材料并支持插值的表示。我们全面审查和讨论目前的表示和它们之间的关系,使用统一的数学框架的基础上多体函数,组平均,张量积。对于选定的国家的最先进的表示,我们比较能量预测的有机分子,二元合金,和Al-Ga-In倍半氧化物的数值实验控制的数据分布,回归方法,和超参数优化。
英文摘要:
Computational study of molecules and materials from first principles is a cornerstone of physics, chemistry, and materials science, but limited by the cost of accurate and precise simulations. In settings involving many simulations, machine learning can reduce these costs, often by orders of magnitude, by interpolating between reference simulations. This requires representations that describe any molecule or material and support interpolation. We comprehensively review and discuss current representations and relations between them, using a unified mathematical framework based on many-body functions, group averaging, and tensor products. For selected state-of-the-art representations, we compare energy predictions for organic molecules, binary alloys, and Al-Ga-In sesquioxides in numerical experiments controlled for data distribution, regression method, and hyper-parameter optimization.
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。