Transfer learning in predicting quantum many-body dynamics: from physical observables to entanglement entropy

IF 5.6 2区 物理与天体物理 Q1 PHYSICS, MULTIDISCIPLINARY
Philipp Schmidt, Florian Marquardt and Naeimeh Mohseni
{"title":"Transfer learning in predicting quantum many-body dynamics: from physical observables to entanglement entropy","authors":"Philipp Schmidt, Florian Marquardt and Naeimeh Mohseni","doi":"10.1088/2058-9565/adbd6d","DOIUrl":null,"url":null,"abstract":"Deep neural networks have demonstrated remarkable efficacy in extracting meaningful representations from complex datasets. This has propelled representation learning as a compelling area of research across diverse fields. One interesting open question is how beneficial representation learning can be for quantum many-body physics, with its notoriously high-dimensional state space. In this work, we showcase the capacity of a neural network that was trained on a subset of physical observables of a many-body system to partially acquire an implicit representation of the wave function. We illustrate this by demonstrating the effectiveness of reusing the representation learned by the neural network to enhance the learning process of another quantity derived from the quantum state. In particular, we focus on how the pre-trained neural network can enhance the learning of entanglement entropy. This is of particular interest as directly measuring the entanglement in a many-body system is very challenging, while a subset of physical observables can be easily measured in experiments. We show the pre-trained neural network learns the dynamics of entropy with fewer resources and higher precision in comparison with direct training on the entanglement entropy.","PeriodicalId":20821,"journal":{"name":"Quantum Science and Technology","volume":"14 1","pages":""},"PeriodicalIF":5.6000,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Quantum Science and Technology","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1088/2058-9565/adbd6d","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PHYSICS, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Deep neural networks have demonstrated remarkable efficacy in extracting meaningful representations from complex datasets. This has propelled representation learning as a compelling area of research across diverse fields. One interesting open question is how beneficial representation learning can be for quantum many-body physics, with its notoriously high-dimensional state space. In this work, we showcase the capacity of a neural network that was trained on a subset of physical observables of a many-body system to partially acquire an implicit representation of the wave function. We illustrate this by demonstrating the effectiveness of reusing the representation learned by the neural network to enhance the learning process of another quantity derived from the quantum state. In particular, we focus on how the pre-trained neural network can enhance the learning of entanglement entropy. This is of particular interest as directly measuring the entanglement in a many-body system is very challenging, while a subset of physical observables can be easily measured in experiments. We show the pre-trained neural network learns the dynamics of entropy with fewer resources and higher precision in comparison with direct training on the entanglement entropy.
预测量子多体动力学的迁移学习:从物理观测到纠缠熵
深度神经网络在从复杂数据集中提取有意义的表示方面表现出显著的功效。这推动了表征学习成为跨不同领域的一个引人注目的研究领域。一个有趣的开放问题是,表征学习对量子多体物理有多大好处,因为量子多体物理是出了名的高维状态空间。在这项工作中,我们展示了在多体系统的物理观测子集上训练的神经网络的能力,以部分获得波函数的隐式表示。我们通过证明重用神经网络学习到的表示来增强从量子态派生的另一个量的学习过程的有效性来说明这一点。我们特别关注预训练的神经网络如何增强纠缠熵的学习。这是特别有趣的,因为直接测量多体系统中的纠缠是非常具有挑战性的,而物理观测的子集可以很容易地在实验中测量。我们表明,与直接训练纠缠熵相比,预训练的神经网络以更少的资源和更高的精度学习熵的动态。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Quantum Science and Technology
Quantum Science and Technology Materials Science-Materials Science (miscellaneous)
CiteScore
11.20
自引率
3.00%
发文量
133
期刊介绍: Driven by advances in technology and experimental capability, the last decade has seen the emergence of quantum technology: a new praxis for controlling the quantum world. It is now possible to engineer complex, multi-component systems that merge the once distinct fields of quantum optics and condensed matter physics. Quantum Science and Technology is a new multidisciplinary, electronic-only journal, devoted to publishing research of the highest quality and impact covering theoretical and experimental advances in the fundamental science and application of all quantum-enabled technologies.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信