Machine learning corrected quantum dynamics calculations
Machine learning corrected quantum dynamics calculations
复制标题
DOI：
10.1103/physrevresearch.2.032051
复制
发表时间：
2020-01
期刊：
影响因子：
--
通讯作者：
A. Jasinski;J. Montaner;R. C. Forrey;B. Yang;P. Stancil;N. Balakrishnan;J. Dai;R. A. Vargas-Hern'andez;R. Krems
中科院分区：
文献类型：
--
作者：
A. Jasinski;J. Montaner;R. C. Forrey;B. Yang;P. Stancil;N. Balakrishnan;J. Dai;R. A. Vargas-Hern'andez;R. Krems
除低维系统外，所有低能系统的量子散射计算都必须依赖于近似。所有的近似都会引入误差。这些误差的影响通常很难评估，因为它们取决于哈密顿参数和研究中的特定观察值。在这里，我们说明了一个通用的，系统和近似无关的方法，以提高量子动力学近似的精度。该方法基于贝叶斯机器学习(BML)算法，通过少量严格的结果和大量的近似计算进行训练，得到准确捕捉动力学结果对量子动力学参数的依赖关系的ML模型。最重要的是，本工作表明BML模型可以将量子结果推广到不同的动力学过程。因此，通过对某一非弹性相变的近似结果和严格结果相结合来训练的ML模型可以对不同的相变做出准确的预测，而不需要严格的计算。这为提高严格散射计算所不能及的量子跃迁的近似计算精度提供了可能。
Quantum scattering calculations for all but low-dimensional systems at low energies must rely on approximations. All approximations introduce errors. The impact of these errors is often difficult to assess because they depend on the Hamiltonian parameters and the particular observable under study. Here, we illustrate a general, system and approximation-independent, approach to improve the accuracy of quantum dynamics approximations. The method is based on a Bayesian machine learning (BML) algorithm that is trained by a small number of rigorous results and a large number of approximate calculations, resulting in ML models that accurately capture the dependence of the dynamics results on the quantum dynamics parameters. Most importantly, the present work demonstrates that the BML models can generalize quantum results to different dynamical processes. Thus, a ML model trained by a combination of approximate and rigorous results for a certain inelastic transition can make accurate predictions for different transitions without rigorous calculations. This opens the possibility of improving the accuracy of approximate calculations for quantum transitions that are out of reach of rigorous scattering calculations.