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 1801.04823physics.comp-ph
收藏

基于机器学习的高效非参数$n$-体力场

Efficient nonparametric $n$-body force fields from machine learning

Aldo Glielmo, Claudio Zeni, Alessandro De Vita

摘要:

我们提供了一个定义和明确的表达式$n$体高斯过程(GP)内核,可以学习任何原子间的相互作用发生在一个物理系统中,高达$n$体的贡献,为任何值的$n$。该系列是完整的,因为它可以表明,"通用逼近器"平方指数内核可以写为$n$体内核的总和。这些配方能够为每个目标系统选择最佳有效的力模型,并通过对各种材料的广泛测试得到证实。我们还描述了如何的$n$体内核可以"映射"等价表示,提供数据库大小无关的预测,因此至关重要的是更有效的。我们明确地进行这种映射过程的第一个非平凡的(3体)内核的系列,并表明,这再现了GP预测的力量与$\text{meV/} Å$的准确性,同时被数量级更快。这些结果为使用新的力模型(这里称为"M-FF")开辟了道路,这些力模型在计算上与其相应的标准参数化$n$-身体力场一样快,同时保留了非参数特性,易于训练和验证,以及最近提出的最佳机器学习潜力的准确性。

英文摘要:

We provide a definition and explicit expressions for $n$-body Gaussian Process (GP) kernels which can learn any interatomic interaction occurring in a physical system, up to $n$-body contributions, for any value of $n$. The series is complete, as it can be shown that the "universal approximator" squared exponential kernel can be written as a sum of $n$-body kernels. These recipes enable the choice of optimally efficient force models for each target system, as confirmed by extensive testing on various materials. We furthermore describe how the $n$-body kernels can be "mapped" on equivalent representations that provide database-size-independent predictions and are thus crucially more efficient. We explicitly carry out this mapping procedure for the first non-trivial (3-body) kernel of the series, and show that this reproduces the GP-predicted forces with $\text{meV/} Å$ accuracy while being orders of magnitude faster. These results open the way to using novel force models (here named "M-FFs") that are computationally as fast as their corresponding standard parametrised $n$-body force fields, while retaining the nonparametric character, the ease of training and validation, and the accuracy of the best recently proposed machine learning potentials.

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。

↑