AI 中文总结
研究分子动力学模拟中两个状态转变时的反应概率函数，提出基于伊藤公式的新损失函数，通过神经网络参数最小化学习该函数，经比较和耦合策略改进，该方法仅需初始反应物和产物状态知识即可迭代学习。
AI 中文摘要
许多分子动力学模拟旨在研究两个状态（从反应物到产物）之间的转变。在此背景下，反应概率函数（给定分子构型时，在反应物状态之前到达产物状态的概率）是关键量，因其是重要性采样或分裂技术等罕见事件模拟方法的最优重要性函数。这些方法用于采样反应路径系综并估计例如跃迁速率。然而，由于构型空间的高维性，学习这样一个函数通常具有挑战性。在这项工作中，回顾了构建近似反应概率函数的现有方法后，提出了基于伊藤公式应用的新损失函数，通过神经网络参数的最小化过程来学习反应概率函数。在将这种新方法与基于穆勒 - 布朗势的现有程序进行比较后，引入了与自适应多级分裂方法的耦合策略，通过更好地采样反应轨迹来更好地近似反应概率函数。这种迭代学习反应概率函数的方法最初仅需要反应物和产物状态的知识。
英文摘要
Many molecular dynamics simulations aim at studying transitions between two states (from reactants to products). In this context, the committor function (which gives for a given molecular configuration the probability to reach the product state before the reactant state) is a pivotal quantity, in particular because it is the optimal importance function for rare event simulation methods such as importance sampling or splitting techniques. These methods are used to sample the reactive path ensemble, and estimate for example the transition rate. However, learning such a function is generally a challenging task due to the high dimensionality of the configuration space. In this work, after reviewing the existing methodologies to construct approximate committor functions, a new loss function based on the application of Itō's formula is proposed to learn the committor function with a minimization procedure on the parameters of a neural network. After comparing this novel approach to existing procedures on the Müller--Brown potential, we introduce a coupling strategy with the Adaptive Multilevel Splitting method to better approximate the committor function using a better sampling of the reactive trajectories. This methodology in which the committor function is iteratively learned only requires initially the knowledge of the reactant and product states.
Comments37 ages in the main text with 9 Figures and 8 pages in the supplementary material
