arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.02524physics.data-anphysics.chem-phphysics.comp-ph
收藏

非正态误差分布对量子机器学习模型的基准测试和排名的影响

Impact of non-normal error distributions on the benchmarking and ranking of Quantum Machine Learning models

Pascal Pernot, Bing Huang, Andreas Savin

摘要:

量子机器学习模型在原子模拟社区中获得了巨大的吸引力。通常,使用学习曲线(预测误差与训练集大小)评估和比较相对模型性能。本文说明了使用平均绝对误差(MAE)进行基准测试的局限性,这在非正态误差分布的情况下尤其重要。在CCSD(T)/cc-pVDZ理论水平上,分析了基于SLATM表示和L2距离度量的核岭回归(KRR-SLATM-L2)对QM 7 b分子有效原子化能的预测误差分布.还评估了参考CCSD(T)值的相同基组的HF和MP2的误差分布,并与KRR模型进行了比较。我们表明,在QM 7 b数据集上的KRR-SLATM-L2方法的真实性能通过平均绝对误差评估得很差,并且在学习集的自适应之后可以显着改善。

英文摘要:

Quantum machine learning models have been gaining significant traction within atomistic simulation communities. Conventionally, relative model performances are being assessed and compared using learning curves (prediction error vs. training set size). This article illustrates the limitations of using the Mean Absolute Error (MAE) for benchmarking, which is particularly relevant in the case of non-normal error distributions. We analyze more specifically the prediction error distribution of the kernel ridge regression with SLATM representation and L 2 distance metric (KRR-SLATM-L2) for effective atomization energies of QM7b molecules calculated at the level of theory CCSD(T)/cc-pVDZ. Error distributions of HF and MP2 at the same basis set referenced to CCSD(T) values were also assessed and compared to the KRR model. We show that the true performance of the KRR-SLATM-L2 method over the QM7b dataset is poorly assessed by the Mean Absolute Error, and can be notably improved after adaptation of the learning set.

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。

↑