利用机器学习预测杂质谱函数

Erica J. Sturm, Matthew R. Carbone, D. Lu, A. Weichselbaum, R. Konik
{"title":"利用机器学习预测杂质谱函数","authors":"Erica J. Sturm, Matthew R. Carbone, D. Lu, A. Weichselbaum, R. Konik","doi":"10.1103/PhysRevB.103.245118","DOIUrl":null,"url":null,"abstract":"The Anderson Impurity Model (AIM) is a canonical model of quantum many-body physics. Here we investigate whether machine learning models, both neural networks (NN) and kernel ridge regression (KRR), can accurately predict the AIM spectral function in all of its regimes, from empty orbital, to mixed valence, to Kondo. To tackle this question, we construct two large spectral databases containing approximately 410k and 600k spectral functions of the single-channel impurity problem. We show that the NN models can accurately predict the AIM spectral function in all of its regimes, with point-wise mean absolute errors down to 0.003 in normalized units. We find that the trained NN models outperform models based on KRR and enjoy a speedup on the order of $10^5$ over traditional AIM solvers. The required size of the training set of our model can be significantly reduced using furthest point sampling in the AIM parameter space, which is important for generalizing our method to more complicated multi-channel impurity problems of relevance to predicting the properties of real materials.","PeriodicalId":8511,"journal":{"name":"arXiv: Strongly Correlated Electrons","volume":"24 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2020-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Predicting impurity spectral functions using machine learning\",\"authors\":\"Erica J. Sturm, Matthew R. Carbone, D. Lu, A. Weichselbaum, R. Konik\",\"doi\":\"10.1103/PhysRevB.103.245118\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The Anderson Impurity Model (AIM) is a canonical model of quantum many-body physics. Here we investigate whether machine learning models, both neural networks (NN) and kernel ridge regression (KRR), can accurately predict the AIM spectral function in all of its regimes, from empty orbital, to mixed valence, to Kondo. To tackle this question, we construct two large spectral databases containing approximately 410k and 600k spectral functions of the single-channel impurity problem. We show that the NN models can accurately predict the AIM spectral function in all of its regimes, with point-wise mean absolute errors down to 0.003 in normalized units. We find that the trained NN models outperform models based on KRR and enjoy a speedup on the order of $10^5$ over traditional AIM solvers. The required size of the training set of our model can be significantly reduced using furthest point sampling in the AIM parameter space, which is important for generalizing our method to more complicated multi-channel impurity problems of relevance to predicting the properties of real materials.\",\"PeriodicalId\":8511,\"journal\":{\"name\":\"arXiv: Strongly Correlated Electrons\",\"volume\":\"24 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv: Strongly Correlated Electrons\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1103/PhysRevB.103.245118\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv: Strongly Correlated Electrons","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1103/PhysRevB.103.245118","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

摘要

安德森杂质模型(AIM)是量子多体物理的一个经典模型。在这里,我们研究了机器学习模型,包括神经网络(NN)和核脊回归(KRR),是否可以准确地预测AIM的所有谱函数,从空轨道到混合价态,再到近藤。为了解决这个问题,我们构建了两个大型的光谱数据库,其中包含大约410k和600k的单通道杂质问题的光谱函数。我们表明,神经网络模型可以准确地预测AIM谱函数的所有区域,在归一化单位下,逐点平均绝对误差降至0.003。我们发现训练后的神经网络模型优于基于KRR的模型,并且比传统的AIM求解器加速了10^5美元。使用AIM参数空间中的最远点采样可以显著减少模型所需的训练集大小,这对于将我们的方法推广到与预测实际材料性质相关的更复杂的多通道杂质问题具有重要意义。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Predicting impurity spectral functions using machine learning
The Anderson Impurity Model (AIM) is a canonical model of quantum many-body physics. Here we investigate whether machine learning models, both neural networks (NN) and kernel ridge regression (KRR), can accurately predict the AIM spectral function in all of its regimes, from empty orbital, to mixed valence, to Kondo. To tackle this question, we construct two large spectral databases containing approximately 410k and 600k spectral functions of the single-channel impurity problem. We show that the NN models can accurately predict the AIM spectral function in all of its regimes, with point-wise mean absolute errors down to 0.003 in normalized units. We find that the trained NN models outperform models based on KRR and enjoy a speedup on the order of $10^5$ over traditional AIM solvers. The required size of the training set of our model can be significantly reduced using furthest point sampling in the AIM parameter space, which is important for generalizing our method to more complicated multi-channel impurity problems of relevance to predicting the properties of real materials.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Electronic and magnetic properties of iridium ilmenites $A$IrO$_3$ ($A=$ Mg, Zn, and Mn). Landau-Fermi liquids in disguise Diffusion in the Anderson model in higher dimensions Discovery of an ultra-quantum spin liquid Topological excitations in quasi two-dimensional quantum magnets with weak interlayer interactions
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1