In recent years the machine learning techniques have shown a great potential in various problems from a multitude of disciplines, including materials design and drug discovery. The high computational speed on the one hand and the accuracy comparable to that of DFT on another hand make machine learning algorithms efficient for high-throughput screening through chemical and configurational space. However, the machine learning algorithms available in the literature require large training datasets to reach the chemical accuracy and also show large errors for the so-called outliers - the out-of-sample molecules, not well-represented in the training set. In the present paper we propose a new machine learning algorithm for predicting molecular properties that addresses these two issues: it is based on a local model of interatomic interactions providing high accuracy when trained on relatively small training sets and an active learning algorithm of optimally choosing the training set that significantly reduces the errors for the outliers. We compare our model to the other state-of-the-art algorithms from the literature on the widely used benchmark tests.
The loss of the property of locality of the kernel in high-dimensional Gaussian process regression on the example of the fitting of molecular potential energy surfaces
Time-Dependent Density Matrix Renormalization Group Algorithms for Nearly Exact Absorption and Fluorescence Spectra of Molecular Aggregates at Both Zero and Finite Temperature
Efficient Chemical Space Exploration Using Active Learning Based on Marginalized Graph Kernel: an Application for Predicting the Thermodynamic Properties of Alkanes with Molecular Simulation
Shanghai Jiao Tong University（上海交通大学）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；Purdue University（普渡大学）
Automated Calculation of Thermal Rate Coefficients using Ring Polymer Molecular Dynamics and Machine-Learning Interatomic Potentials with Active Learning
Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations
Institute of Nanotechnology, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院纳米技术研究所）；Institute of Theoretical Informatics, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院理论信息学研究所）
Ring Polymer Molecular Dynamics and Active Learning of Moment Tensor Potential for Gas-Phase Barrierless Reactions: Application to S + H2
环状聚合物分子动力学（RPMD）已被证明是计算各种化学反应热速率系数的一种精确方法。为了更广泛地应用这种方法，需要有效的方法来生成底层的全维势能面（PES）和相应的能量梯度。最近，我们提出了一个完全自动化的程序，该程序基于将原始RPMDrate代码与使用矩张量势的PES动态主动学习相结合，并成功地将其应用于两个代表性的热活化化学反应[I]。S. Novikov，Y. V. Suleimanov，A. V. Shapeev，物理化学物理，29503-29512（2018）]。在这项工作中，使用原型插入化学反应S + H $_2$，我们表明，这一过程同样适用于另一类化学反应。我们发现，相应的PES可以通过拟合到不到1500自动生成的结构，而RPMD速率系数显示偏离参考值内的RPMDrate的典型收敛误差。我们注意到，更多的结构积累在实时传播的动态因子（再交叉因子），而不是以前的研究。我们还观察到，在进入络合物形成井之前，沿着反应坐标的相对平坦的自由能分布可能导致定位不太收敛的PES的自由能表面的最大值的问题。然而，最终的RPMD速率系数与分割表面的位置无关，这使得它不会受到这个问题的影响，从而将必要结构的总数保持在几千以内。我们的工作的结论是，在未来，所提出的方法可以应用到现实的复杂的化学反应与各种能源配置文件。
