Magnetic State Generation using Hamiltonian Guided Variational Autoencoder with Spin Structure Stabilization.
Magnetic State Generation using Hamiltonian Guided Variational Autoencoder with Spin Structure Stabilization.
复制标题
DOI：
10.1002/advs.202004795
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Won C
中科院分区：
文献类型：
--
作者：
Kwon HY;Yoon HG;Park SM;Lee DB;Choi JW;Won C
物理状态的数值生成对于所有科学研究领域都是必不可少的。数值生成器的作用不仅限于理解实验结果；它还可以用来预测或研究未知系统的特征。设计了一种变分自动编码器模型，并将其应用于磁系统，以产生低局部变形的能量稳定的磁态。通过考虑显式磁哈密顿量来最小化训练过程中的能量，使得自旋结构稳定化成为可能。该模型的一个显著优点是，即使基态不一定包括在训练过程中，生成器也可以通过增加稳定的作用来创建自旋组态的长程有序基态。期望所提出的哈密顿引导的产生式模型能够在各种科学研究领域中的数值方法方面带来巨大的进步。通过将显式哈密顿量引入到训练过程中，设计了一个能量最小化变分自动编码器模型，以产生能量稳定的物理态。该模型的一个显著优点是，即使基态不一定包括在训练过程中，生成器也可以产生各种系统的基态。
Numerical generation of physical states is essential to all scientific research fields. The role of a numerical generator is not limited to understanding experimental results; it can also be employed to predict or investigate characteristics of uncharted systems. A variational autoencoder model is devised and applied to a magnetic system to generate energetically stable magnetic states with low local deformation. The spin structure stabilization is made possible by taking the explicit magnetic Hamiltonian into account to minimize energy in the training process. A significant advantage of the model is that the generator can create a long‐range ordered ground state of spin configuration by increasing the role of stabilization even if the ground states are not necessarily included in the training process. It is expected that the proposed Hamiltonian‐guided generative model can bring about great advances in numerical approaches used in various scientific research fields. An energy‐minimization variational autoencoder model is devised to generate energetically stable physical states by taking the explicit Hamiltonian into the training process. A significant advantage of the model is that the generator can produce the ground states of various systems even if the ground states are not necessarily included in the training process.
登录
查看更多内容
影响因子：
2.7
作者：
BOGDANOV, A;HUBERT, A
通讯作者：
HUBERT, A
影响因子：
56.9
作者：
Carleo, Giuseppe;Troyer, Matthias
通讯作者：
Troyer, Matthias
影响因子：
2.7
作者：
Luchnikov IA;Ryzhov A;Stas PJ;Filippov SN;Ouerdane H
通讯作者：
Ouerdane H
影响因子：
2.7
作者：
Kwon, H. Y.;Won, C.
通讯作者：
Won, C.
影响因子：
3.7
作者：
Kwon, H. Y.;Kim, N. J.;Won, C.
通讯作者：
Won, C.