arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.07599physics.comp-phcs.LG
收藏

用于固体的可迁移神经网络波函数

Transferable Neural Wavefunctions for Solids

Faculty of Mathematics, University of Vienna(维也纳大学数学学院);Department of Physics, Imperial College London(帝国理工学院物理系);Johann Radon Institute for Computational and Applied Mathematics, Austrian Academy of Sciences(奥地利科学院约翰·拉登计算与应用数学研究所)

Leon Gerard, Michael Scherbela, Halvard Sutterud, Matthew Foulkes, Philipp Grohs

AI总结:

针对固体体系DL-VMC需逐体系优化网络成本高的问题,提出跨几何、边界条件、超胞尺寸优化单个ansatz的方法,并实现预训练网络从LiH 2×2×2到3×3×3超胞的迁移,大幅降低优化步数。

摘要:

基于深度学习的变分蒙特卡洛方法(DL-VMC)近期已成为求解多电子薛定谔方程近似解的一种高精度方法。尽管其计算量随电子数的标度关系良好,为$\boldsymbol{\text{O}(n_\text{el}^{4})}$,但DL-VMC的实际应用价值受限于需为每个研究体系单独优化神经网络权重的高昂成本。为缓解这一问题,近期研究提出跨多个体系优化单个神经网络的方案,降低了单个体系的计算成本。本文将该方法拓展至固体领域——这类研究通常需要针对不同几何结构、边界条件和超胞尺寸开展相似但有差异的计算。我们展示了如何在所有这些变体条件下优化单个试探波函数(ansatz),将所需的优化步数减少了一个数量级。此外,我们还挖掘了预训练网络的迁移能力:将在LiH的2×2×2超胞上预训练的网络成功迁移至3×3×3超胞,与已有工作相比,模拟该大体系所需的优化步数减少了50倍。

英文摘要:

Deep-Learning-based Variational Monte Carlo (DL-VMC) has recently emerged as a highly accurate approach for finding approximate solutions to the many-electron Schrödinger equation. Despite its favorable scaling with the number of electrons, $\mathcal{O}(n_\text{el}^{4})$, the practical value of DL-VMC is limited by the high cost of optimizing the neural network weights for every system studied. To mitigate this problem, recent research has proposed optimizing a single neural network across multiple systems, reducing the cost per system. Here we extend this approach to solids, where similar but distinct calculations using different geometries, boundary conditions, and supercell sizes are often required. We show how to optimize a single ansatz across all of these variations, reducing the required number of optimization steps by an order of magnitude. Furthermore, we exploit the transfer capabilities of a pre-trained network. We successfully transfer a network, pre-trained on 2x2x2 supercells of LiH, to 3x3x3 supercells. This reduces the number of optimization steps required to simulate the large system by a factor of 50 compared to previous work.

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。

↑