论文标题
在化学复合空间中的初始机器学习
Ab initio machine learning in chemical compound space
论文作者
论文摘要
化学复合空间（CCS）是所有理论上可以想象的化学元素和（元）稳定几何形状的组合组合的集合，它们是巨大的。因此，除了最小的子集和最简单的特性外，所有基于原理的虚拟采样，例如寻找具有理想特性的新分子或表现出理想特性的材料。我们审查了旨在使用基于（i）合成数据的现代机器学习技术来应对这一挑战的研究，该技术通常使用基于量子力学的方法生成，以及（ii）受量子力学启发的模型体系结构。这种基于量子力学的机器学习（QML）方法将统计替代模型的数值效率与{\ em ab instio}有关物质的视图结合在一起。它们严格反映了基本的物理，以达到CCS之间的普遍性和可转移性。虽然最新的量子问题近似值会施加严重的计算瓶颈，但最新的基于QML的开发表明了在不牺牲量子力学的预测能力的情况下实质加速的可能性。
Chemical compound space (CCS), the set of all theoretically conceivable combinations of chemical elements and (meta-)stable geometries that make up matter, is colossal. The first principles based virtual sampling of this space, for example in search of novel molecules or materials which exhibit desirable properties, is therefore prohibitive for all but the smallest sub-sets and simplest properties. We review studies aimed at tackling this challenge using modern machine learning techniques based on (i) synthetic data, typically generated using quantum mechanics based methods, and (ii) model architectures inspired by quantum mechanics. Such Quantum mechanics based Machine Learning (QML) approaches combine the numerical efficiency of statistical surrogate models with an {\em ab initio} view on matter. They rigorously reflect the underlying physics in order to reach universality and transferability across CCS. While state-of-the-art approximations to quantum problems impose severe computational bottlenecks, recent QML based developments indicate the possibility of substantial acceleration without sacrificing the predictive power of quantum mechanics.
