以对称性与退火补充循环神经网络波函数以提升精度
无序系统与神经网络
2024-01-17 v2 强关联电子
机器学习
计算物理
摘要
循环神经网络(RNNs)是一类源自人工智能范式、并在自然语言处理领域促成诸多有趣进展的神经网络。有趣的是,这些架构被证明是近似量子系统基态的强大拟设。在此,我们基于 [Phys. Rev. Research 2, 023358 (2020)] 的结果,构建了二维上更强大的 RNN 波函数拟设。我们利用对称性与退火,在平方晶格与三角晶格上获得二维(2D)海森堡模型基态能量的精确估计。我们表明,在三角晶格上系统尺寸大于或等于 14×14 时,我们的方法优于密度矩阵重整化群(DMRG)。
引用
@article{arxiv.2207.14314,
title = {Supplementing Recurrent Neural Network Wave Functions with Symmetry and Annealing to Improve Accuracy},
author = {Mohamed Hibat-Allah and Roger G. Melko and Juan Carrasquilla},
journal= {arXiv preprint arXiv:2207.14314},
year = {2024}
}
备注
11 pages, 4 figures, 1 table. Corrected typos. Originally published in Machine Learning and the Physical Sciences Workshop (NeurIPS 2021), see: https://ml4physicalsciences.github.io/2021/files/NeurIPS_ML4PS_2021_92.pdf. Our reproducibility code can be found at https://github.com/mhibatallah/RNNWavefunctions