NISQ 时代量子机器学习的泛化误差约束 -- 综述

Bikram Khanal, Pablo Rivas, Arun Sanjel, Korn Sooksatra, Ernesto Quevedo, Alejandro Rodriguez
{"title":"NISQ 时代量子机器学习的泛化误差约束 -- 综述","authors":"Bikram Khanal, Pablo Rivas, Arun Sanjel, Korn Sooksatra, Ernesto Quevedo, Alejandro Rodriguez","doi":"arxiv-2409.07626","DOIUrl":null,"url":null,"abstract":"Despite the mounting anticipation for the quantum revolution, the success of\nQuantum Machine Learning (QML) in the Noisy Intermediate-Scale Quantum (NISQ)\nera hinges on a largely unexplored factor: the generalization error bound, a\ncornerstone of robust and reliable machine learning models. Current QML\nresearch, while exploring novel algorithms and applications extensively, is\npredominantly situated in the context of noise-free, ideal quantum computers.\nHowever, Quantum Circuit (QC) operations in NISQ-era devices are susceptible to\nvarious noise sources and errors. In this article, we conduct a Systematic\nMapping Study (SMS) to explore the state-of-the-art generalization bound for\nsupervised QML in NISQ-era and analyze the latest practices in the field. Our\nstudy systematically summarizes the existing computational platforms with\nquantum hardware, datasets, optimization techniques, and the common properties\nof the bounds found in the literature. We further present the performance\naccuracy of various approaches in classical benchmark datasets like the MNIST\nand IRIS datasets. The SMS also highlights the limitations and challenges in\nQML in the NISQ era and discusses future research directions to advance the\nfield. Using a detailed Boolean operators query in five reliable indexers, we\ncollected 544 papers and filtered them to a small set of 37 relevant articles.\nThis filtration was done following the best practice of SMS with well-defined\nresearch questions and inclusion and exclusion criteria.","PeriodicalId":501226,"journal":{"name":"arXiv - PHYS - Quantum Physics","volume":"20 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Generalization Error Bound for Quantum Machine Learning in NISQ Era -- A Survey\",\"authors\":\"Bikram Khanal, Pablo Rivas, Arun Sanjel, Korn Sooksatra, Ernesto Quevedo, Alejandro Rodriguez\",\"doi\":\"arxiv-2409.07626\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Despite the mounting anticipation for the quantum revolution, the success of\\nQuantum Machine Learning (QML) in the Noisy Intermediate-Scale Quantum (NISQ)\\nera hinges on a largely unexplored factor: the generalization error bound, a\\ncornerstone of robust and reliable machine learning models. Current QML\\nresearch, while exploring novel algorithms and applications extensively, is\\npredominantly situated in the context of noise-free, ideal quantum computers.\\nHowever, Quantum Circuit (QC) operations in NISQ-era devices are susceptible to\\nvarious noise sources and errors. In this article, we conduct a Systematic\\nMapping Study (SMS) to explore the state-of-the-art generalization bound for\\nsupervised QML in NISQ-era and analyze the latest practices in the field. Our\\nstudy systematically summarizes the existing computational platforms with\\nquantum hardware, datasets, optimization techniques, and the common properties\\nof the bounds found in the literature. We further present the performance\\naccuracy of various approaches in classical benchmark datasets like the MNIST\\nand IRIS datasets. The SMS also highlights the limitations and challenges in\\nQML in the NISQ era and discusses future research directions to advance the\\nfield. Using a detailed Boolean operators query in five reliable indexers, we\\ncollected 544 papers and filtered them to a small set of 37 relevant articles.\\nThis filtration was done following the best practice of SMS with well-defined\\nresearch questions and inclusion and exclusion criteria.\",\"PeriodicalId\":501226,\"journal\":{\"name\":\"arXiv - PHYS - Quantum Physics\",\"volume\":\"20 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Quantum Physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07626\",\"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 - PHYS - Quantum Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07626","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

尽管人们对量子革命的期待日益高涨,但量子机器学习(QML)在中量级噪声量子(NISQ)时代能否取得成功,很大程度上取决于一个尚未探索的因素:泛化误差边界,这是稳健可靠的机器学习模型的基石。目前的 QML 研究虽然广泛探索了新算法和应用,但主要是在无噪声、理想量子计算机的背景下进行的。然而,NISQ 时代设备中的量子电路(QC)操作容易受到各种噪声源和误差的影响。在本文中,我们开展了一项系统映射研究(SMS),以探索 NISQ 时代有监督 QML 的最先进泛化边界,并分析该领域的最新实践。我们的研究系统地总结了现有的量子硬件计算平台、数据集、优化技术以及文献中发现的边界的共同属性。我们进一步介绍了各种方法在经典基准数据集(如 MNIST 和 IRIS 数据集)中的性能精度。SMS 还强调了 NISQ 时代 QML 的局限性和挑战,并讨论了推进该领域发展的未来研究方向。通过在五个可靠的索引器中使用详细的布尔运算符查询,我们收集到了 544 篇论文,并将其筛选为 37 篇相关文章。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Generalization Error Bound for Quantum Machine Learning in NISQ Era -- A Survey
Despite the mounting anticipation for the quantum revolution, the success of Quantum Machine Learning (QML) in the Noisy Intermediate-Scale Quantum (NISQ) era hinges on a largely unexplored factor: the generalization error bound, a cornerstone of robust and reliable machine learning models. Current QML research, while exploring novel algorithms and applications extensively, is predominantly situated in the context of noise-free, ideal quantum computers. However, Quantum Circuit (QC) operations in NISQ-era devices are susceptible to various noise sources and errors. In this article, we conduct a Systematic Mapping Study (SMS) to explore the state-of-the-art generalization bound for supervised QML in NISQ-era and analyze the latest practices in the field. Our study systematically summarizes the existing computational platforms with quantum hardware, datasets, optimization techniques, and the common properties of the bounds found in the literature. We further present the performance accuracy of various approaches in classical benchmark datasets like the MNIST and IRIS datasets. The SMS also highlights the limitations and challenges in QML in the NISQ era and discusses future research directions to advance the field. Using a detailed Boolean operators query in five reliable indexers, we collected 544 papers and filtered them to a small set of 37 relevant articles. This filtration was done following the best practice of SMS with well-defined research questions and inclusion and exclusion criteria.
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
×
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