Chen-Yu Liu, Chu-Hsuan Abraham Lin, Kuan-Cheng Chen
{"title":"带有张量网络映射模型和分布式电路解析的量子列车","authors":"Chen-Yu Liu, Chu-Hsuan Abraham Lin, Kuan-Cheng Chen","doi":"arxiv-2409.06992","DOIUrl":null,"url":null,"abstract":"In the Quantum-Train (QT) framework, mapping quantum state measurements to\nclassical neural network weights is a critical challenge that affects the\nscalability and efficiency of hybrid quantum-classical models. The traditional\nQT framework employs a multi-layer perceptron (MLP) for this task, but it\nstruggles with scalability and interpretability. To address these issues, we\npropose replacing the MLP with a tensor network-based model and introducing a\ndistributed circuit ansatz designed for large-scale quantum machine learning\nwith multiple small quantum processing unit nodes. This approach enhances\nscalability, efficiently represents high-dimensional data, and maintains a\ncompact model structure. Our enhanced QT framework retains the benefits of\nreduced parameter count and independence from quantum resources during\ninference. Experimental results on benchmark datasets demonstrate that the\ntensor network-based QT framework achieves competitive performance with\nimproved efficiency and generalization, offering a practical solution for\nscalable hybrid quantum-classical machine learning.","PeriodicalId":501226,"journal":{"name":"arXiv - PHYS - Quantum Physics","volume":"31 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Quantum-Train with Tensor Network Mapping Model and Distributed Circuit Ansatz\",\"authors\":\"Chen-Yu Liu, Chu-Hsuan Abraham Lin, Kuan-Cheng Chen\",\"doi\":\"arxiv-2409.06992\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the Quantum-Train (QT) framework, mapping quantum state measurements to\\nclassical neural network weights is a critical challenge that affects the\\nscalability and efficiency of hybrid quantum-classical models. The traditional\\nQT framework employs a multi-layer perceptron (MLP) for this task, but it\\nstruggles with scalability and interpretability. To address these issues, we\\npropose replacing the MLP with a tensor network-based model and introducing a\\ndistributed circuit ansatz designed for large-scale quantum machine learning\\nwith multiple small quantum processing unit nodes. This approach enhances\\nscalability, efficiently represents high-dimensional data, and maintains a\\ncompact model structure. Our enhanced QT framework retains the benefits of\\nreduced parameter count and independence from quantum resources during\\ninference. Experimental results on benchmark datasets demonstrate that the\\ntensor network-based QT framework achieves competitive performance with\\nimproved efficiency and generalization, offering a practical solution for\\nscalable hybrid quantum-classical machine learning.\",\"PeriodicalId\":501226,\"journal\":{\"name\":\"arXiv - PHYS - Quantum Physics\",\"volume\":\"31 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-2409.06992\",\"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-2409.06992","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Quantum-Train with Tensor Network Mapping Model and Distributed Circuit Ansatz
In the Quantum-Train (QT) framework, mapping quantum state measurements to
classical neural network weights is a critical challenge that affects the
scalability and efficiency of hybrid quantum-classical models. The traditional
QT framework employs a multi-layer perceptron (MLP) for this task, but it
struggles with scalability and interpretability. To address these issues, we
propose replacing the MLP with a tensor network-based model and introducing a
distributed circuit ansatz designed for large-scale quantum machine learning
with multiple small quantum processing unit nodes. This approach enhances
scalability, efficiently represents high-dimensional data, and maintains a
compact model structure. Our enhanced QT framework retains the benefits of
reduced parameter count and independence from quantum resources during
inference. Experimental results on benchmark datasets demonstrate that the
tensor network-based QT framework achieves competitive performance with
improved efficiency and generalization, offering a practical solution for
scalable hybrid quantum-classical machine learning.