论文标题
高斯过程回归以进行几何优化
Gaussian Process Regression for Geometry Optimization
论文作者
论文摘要
我们基于高斯工艺回归（GPR）实现了几何优化器，以在势能表面找到最小结构。我们测试了Matérn内核和平方指数核的两次可区分形式。 Matérn内核的表现要好得多。我们详细说明了优化过程。这些包括对GPR产生的步骤进行过多，以获得更高程度的插值与外推。在针对26个测试系统上DL-Find库的L-BFGS优化器的基准测试中，我们发现了新的优化器通常会减少所需的优化步骤的数量。
We implemented a geometry optimizer based on Gaussian process regression (GPR) to find minimum structures on potential energy surfaces. We tested both a two times differentiable form of the Matérn kernel and the squared exponential kernel. The Matérn kernel performs much better. We give a detailed description of the optimization procedures. These include overshooting the step resulting from GPR in order to obtain a higher degree of interpolation vs. extrapolation. In a benchmark against the L-BFGS optimizer of the DL-FIND library on 26 test systems, we found the new optimizer to generally reduce the number of required optimization steps.
