利用可微模拟学习对势
Learning Pair Potentials using Differentiable Simulations
摘要：
从实验或模拟数据中学习对相互作用对于分子模拟具有极大的兴趣。我们提出了一个一般的随机方法学习对相互作用的数据，使用微分模拟（DiffSim）。DiffSim通过分子动力学（MD）模拟定义了基于结构可观测量的损失函数，例如径向分布函数。然后通过随机梯度下降直接学习相互作用势，使用反向传播来计算结构损失度量相对于通过MD模拟的相互作用势的梯度。这种基于梯度的方法非常灵活，可以配置为同时模拟和优化多个系统。例如，可以同时学习不同温度或不同成分的电位。我们证明了恢复简单的对电位，如Lennard-Jones系统，从径向分布函数的方法。我们发现，DiffSim可以用来探测更广泛的功能空间的对电位相比，传统的方法，如迭代玻尔兹曼反演。我们表明，我们的方法可以用来同时适合在不同的组合物和温度下的模拟电位，以提高学习电位的可转移性。
英文摘要：
Learning pair interactions from experimental or simulation data is of great interest for molecular simulations. We propose a general stochastic method for learning pair interactions from data using differentiable simulations (DiffSim). DiffSim defines a loss function based on structural observables, such as the radial distribution function, through molecular dynamics (MD) simulations. The interaction potentials are then learned directly by stochastic gradient descent, using backpropagation to calculate the gradient of the structural loss metric with respect to the interaction potential through the MD simulation. This gradient-based method is flexible and can be configured to simulate and optimize multiple systems simultaneously. For example, it is possible to simultaneously learn potentials for different temperatures or for different compositions. We demonstrate the approach by recovering simple pair potentials, such as Lennard-Jones systems, from radial distribution functions. We find that DiffSim can be used to probe a wider functional space of pair potentials compared to traditional methods like Iterative Boltzmann Inversion. We show that our methods can be used to simultaneously fit potentials for simulations at different compositions and temperatures to improve the transferability of the learned potentials.
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。
