论文标题
改善高斯过程回归基于原子间电位的不确定性定量
Improved uncertainty quantification for Gaussian process regression based interatomic potentials
论文作者
论文摘要
目前，基于概率学习方法（例如高斯过程回归（GPR））基于概率学习方法（MLIP）的误差估计能力（MLIP）目前尚未探索，因为预测错误的趋势以高估了真实错误。我们介绍了基于最大化的边际可能性或使用剩余交叉验证构建的替代可能性的方法，以根据GPR提供改进的误差估计值。我们将这些方法基准为代表AR三聚体的模型，显示出预测误差估计的鲁棒性的显着改善。
The error estimation capability of machine learning interatomic potentials (MLIPs) based on probabilistic learning methods such as Gaussian process regression (GPR) is currently under-exploited, because of the tendancy of the predicted errors to overestimate the true error. We present approaches based on maximising either the marginal likelihood or an alternative likelihood constructed using leave-one-out cross validation to provide improved error estimates for interatomic potentials based on GPR. We benchmarked these approaches on models representing the Ar trimer, showing significant improvements in the robustness of the predicted error estimates.
