Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
复制标题
DOI：
10.1103/physrevb.100.024112
复制
发表时间：
2019-07-30
影响因子：
3.7
通讯作者：
Caro, Miguel A.
中科院分区：
文献类型：
--
作者：
Caro, Miguel A.
我们探索了不同的方法来简化原子位置平滑重叠（SOAP）多体原子描述符的评估[Bartok et al., Phys.修订版 B 87, 184115 (2013).]。我们的目标是提高基于 SOAP 的相似性内核构建的计算效率。虽然这些改进的原子描述符可用于原子属性的一般表征和插值，但它们的主要目标应用是在高斯近似势（GAP）框架内加速评估基于机器学习的原子间势[Bartok et al., Phys.莱特牧师。 104, 136403 (2010)]。我们通过以近似可分离的形式表达原子密度来实现这一目标，从而解耦径向通道和角通道。然后，在给定径向基组的特定选择的情况下，我们以解析形式表达 SOAP 描述符的元素（即原子密度的展开系数）。最后，我们推导了展开系数的递推公式。与以前的实现相比，这种新的基于 SOAP 的描述符可以实现十倍的加速，同时提高远距离原子邻居的径向扩展的稳定性，而不会降低 GAP 模型的插值能力。
We explore different ways to simplify the evaluation of the smooth overlap of atomic positions (SOAP) many-body atomic descriptor [Bartok et al., Phys. Rev. B 87, 184115 (2013).]. Our aim is to improve the computational efficiency of SOAP-based similarity kernel construction. While these improved atomic descriptors can be used for general characterization and interpolation of atomic properties, their main target application is accelerated evaluation of machine-learning-based interatomic potentials within the Gaussian approximation potential (GAP) framework [Bartok et al., Phys. Rev. Lett. 104, 136403 (2010)]. We achieve this objective by expressing the atomic densities in an approximate separable form, which decouples the radial and angular channels. We then express the elements of the SOAP descriptor (i.e., the expansion coefficients for the atomic densities) in analytical form given a particular choice of radial basis set. Finally, we derive recursion formulas for the expansion coefficients. This new SOAP-based descriptor allows for tenfold speedups compared to previous implementations, while improving the stability of the radial expansion for distant atomic neighbors, without degradation of the interpolation power of GAP models.