利用强化学习论量子电路初始映射的最优性

IF 5.8 2区 物理与天体物理 Q1 OPTICS
Norhan Elsayed Amer, Walid Gomaa, Keiji Kimura, Kazunori Ueda, Ahmed El-Mahdy
{"title":"利用强化学习论量子电路初始映射的最优性","authors":"Norhan Elsayed Amer,&nbsp;Walid Gomaa,&nbsp;Keiji Kimura,&nbsp;Kazunori Ueda,&nbsp;Ahmed El-Mahdy","doi":"10.1140/epjqt/s40507-024-00225-1","DOIUrl":null,"url":null,"abstract":"<div><p>Quantum circuit optimization is an inevitable task with the current noisy quantum backends. This task is considered non-trivial due to the varying circuits’ complexities in addition to hardware-specific noise, topology, and limited connectivity. The currently available methods either rely on heuristics for circuit optimization tasks or reinforcement learning with complex unscalable neural networks such as transformers. In this paper, we are concerned with optimizing the initial logical-to-physical mapping selection. Specifically, we investigate whether a reinforcement learning agent with simple scalable neural network is capable of finding a near-optimal logical-to-physical mapping, that would decrease as much as possible additional CNOT gates, only from a fixed-length feature vector. To answer this question, we train a Maskable Proximal Policy Optimization agent to progressively take steps towards a near-optimal logical-to-physical mapping on a 20-qubit hardware architecture. Our results show that our agent coupled with a simple routing evaluation is capable of outperforming other available reinforcement learning and heuristics approaches on 12 out of 19 test benchmarks, achieving geometric mean improvements of 2.2% and 15% over the best available related work and two heuristics approaches, respectively. Additionally, our neural network model scales linearly as the number of qubits increases.</p></div>","PeriodicalId":547,"journal":{"name":"EPJ Quantum Technology","volume":null,"pages":null},"PeriodicalIF":5.8000,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://epjquantumtechnology.springeropen.com/counter/pdf/10.1140/epjqt/s40507-024-00225-1","citationCount":"0","resultStr":"{\"title\":\"On the optimality of quantum circuit initial mapping using reinforcement learning\",\"authors\":\"Norhan Elsayed Amer,&nbsp;Walid Gomaa,&nbsp;Keiji Kimura,&nbsp;Kazunori Ueda,&nbsp;Ahmed El-Mahdy\",\"doi\":\"10.1140/epjqt/s40507-024-00225-1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Quantum circuit optimization is an inevitable task with the current noisy quantum backends. This task is considered non-trivial due to the varying circuits’ complexities in addition to hardware-specific noise, topology, and limited connectivity. The currently available methods either rely on heuristics for circuit optimization tasks or reinforcement learning with complex unscalable neural networks such as transformers. In this paper, we are concerned with optimizing the initial logical-to-physical mapping selection. Specifically, we investigate whether a reinforcement learning agent with simple scalable neural network is capable of finding a near-optimal logical-to-physical mapping, that would decrease as much as possible additional CNOT gates, only from a fixed-length feature vector. To answer this question, we train a Maskable Proximal Policy Optimization agent to progressively take steps towards a near-optimal logical-to-physical mapping on a 20-qubit hardware architecture. Our results show that our agent coupled with a simple routing evaluation is capable of outperforming other available reinforcement learning and heuristics approaches on 12 out of 19 test benchmarks, achieving geometric mean improvements of 2.2% and 15% over the best available related work and two heuristics approaches, respectively. Additionally, our neural network model scales linearly as the number of qubits increases.</p></div>\",\"PeriodicalId\":547,\"journal\":{\"name\":\"EPJ Quantum Technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.8000,\"publicationDate\":\"2024-03-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://epjquantumtechnology.springeropen.com/counter/pdf/10.1140/epjqt/s40507-024-00225-1\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"EPJ Quantum Technology\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://link.springer.com/article/10.1140/epjqt/s40507-024-00225-1\",\"RegionNum\":2,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"OPTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"EPJ Quantum Technology","FirstCategoryId":"101","ListUrlMain":"https://link.springer.com/article/10.1140/epjqt/s40507-024-00225-1","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 0

摘要

量子电路优化是当前噪声量子后端不可避免的任务。除了硬件特有的噪声、拓扑结构和有限的连通性之外,电路的复杂性也各不相同,因此这项任务被视为非同小可。目前可用的方法要么依赖启发式方法来完成电路优化任务,要么使用复杂的不可扩展神经网络(如变压器)进行强化学习。在本文中,我们关注的是初始逻辑到物理映射选择的优化。具体来说,我们要研究的是,具有简单可扩展神经网络的强化学习代理是否能够仅从固定长度的特征向量中找到接近最优的逻辑-物理映射,从而尽可能减少额外的 CNOT 门。为了回答这个问题,我们训练了一个可掩码近端策略优化代理,在 20 量子比特硬件架构上逐步实现接近最优的逻辑到物理映射。我们的结果表明,在 19 个测试基准中的 12 个基准上,我们的代理与简单路由评估相结合,能够超越其他可用的强化学习和启发式方法,与现有的最佳相关工作和两种启发式方法相比,分别实现了 2.2% 和 15% 的几何平均改进。此外,我们的神经网络模型随着比特数的增加而线性扩展。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
On the optimality of quantum circuit initial mapping using reinforcement learning

Quantum circuit optimization is an inevitable task with the current noisy quantum backends. This task is considered non-trivial due to the varying circuits’ complexities in addition to hardware-specific noise, topology, and limited connectivity. The currently available methods either rely on heuristics for circuit optimization tasks or reinforcement learning with complex unscalable neural networks such as transformers. In this paper, we are concerned with optimizing the initial logical-to-physical mapping selection. Specifically, we investigate whether a reinforcement learning agent with simple scalable neural network is capable of finding a near-optimal logical-to-physical mapping, that would decrease as much as possible additional CNOT gates, only from a fixed-length feature vector. To answer this question, we train a Maskable Proximal Policy Optimization agent to progressively take steps towards a near-optimal logical-to-physical mapping on a 20-qubit hardware architecture. Our results show that our agent coupled with a simple routing evaluation is capable of outperforming other available reinforcement learning and heuristics approaches on 12 out of 19 test benchmarks, achieving geometric mean improvements of 2.2% and 15% over the best available related work and two heuristics approaches, respectively. Additionally, our neural network model scales linearly as the number of qubits increases.

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
EPJ Quantum Technology
EPJ Quantum Technology Physics and Astronomy-Atomic and Molecular Physics, and Optics
CiteScore
7.70
自引率
7.50%
发文量
28
审稿时长
71 days
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. EPJ Quantum Technology covers theoretical and experimental advances in subjects including but not limited to the following: Quantum measurement, metrology and lithography Quantum complex systems, networks and cellular automata Quantum electromechanical systems Quantum optomechanical systems Quantum machines, engineering and nanorobotics Quantum control theory Quantum information, communication and computation Quantum thermodynamics Quantum metamaterials The effect of Casimir forces on micro- and nano-electromechanical systems Quantum biology Quantum sensing Hybrid quantum systems Quantum simulations.
×
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:481959085
Book学术官方微信