[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119334-en":3,"doc-seo-119334-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119334,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","Quantum-Train - Rethinking Hybrid Quantum-Classical Machine Learning in the Model Compression Perspective","Quantum-Train (QT) presents a framework that merges quantum computing with classical machine learning to tackle data encoding, model compression, and inference-hardware constraints. Using a quantum neural network together with a classical mapping model, QT achieves strong results even with a slight decrease in accuracy. During training, it reduces parameter count from M to O(polylog(M)), improving model efficiency while lowering generalization errors. Experiments validate its effectiveness on classification tasks, highlighting how quantum advantages can translate into practical ML acceleration under compression.","arXiv :2405 . 11304v2 [ quant-ph] 10 Jun 2024  \nQuantum-Train: Rethinking Hybrid Quantum-Classical Machine Learning in the  \nModel Compression Perspective  \nChen-Yu Liu, 1, 2, ∗ En-Jui Kuo,2, 3,† Chu-Hsuan Abraham Lin,2, 4 Jason Gemsun Young,5 Yeong-Jar Chang,5 Min-Hsiu Hsieh,2,‡ and Hsi-Sheng Goan 1, 6, 7, 3, §  \n1 Graduate Institute of Applied Physics, National Taiwan University, Taipei, Taiwan  \n2 Foxconn Research, Taipei, Taiwan  \n3 Physics Division, National Center for Theoretical Sciences, Taipei, Taiwan  \n4 Department of Electrical and Electronic Engineering, Imperial College London, London, UK  \n5 Industrial Technology Research Institute, Taipei, Taiwan  \n6 Department of Physics and Center for Theoretical Physics, National Taiwan University, Taipei, Taiwan  \n7 Center for Quantum Science and Engineering, National Taiwan University, Taipei, Taiwan  \nWe introduces the Quantum-Train(QT) framework, a novel approach that integrates quantum computing with classical machine learning algorithms to address significant challenges in data encoding, model compression, and inference hardware requirements. Even with a slight decrease inaccuracy, QT achieves remarkable results by employing a quantum neural network alongside a classical mapping model, which significantly reduces the parameter count from M to O(polylog(M)) during training. Our experiments demonstrate QT’s effectiveness in classification tasks, offering insights into its potential to revolutionize machine learning by leveraging quantum computational advantages. This approach not only improves model efficiency but also reduces generalization errors, showcasing QT’s potential across various machine learning applications.  \nI. INTRODUCTION  \nWhilst machine learning (ML) has seen huge success in recent years [1–12], its quantum counterpart quantum machine learning (QML) is also in rapid development. QML represents a groundbreaking intersection that leverages the unparalleled computational powers of quantum mechanics to transform neural network training and functionality. Noticeably, quantum neural networks (QNNs), through quantum superposition and entanglement, are able to evaluate multiple outcomes and results simultaneously. This could theoretically accelerate the training and learning process [13–16] . Besides QNNs, the quantum kernel method stands out by employing quantum operations to craft kernels through the inner products of quantum states. These kernels are subsequently applied to classical data that has been transformed into the quantum realm [17] . Additionally, integrating Grover’s search algorithm with QML for classification tasks offers potential enhancements [18, 19] . QML harbours tremendous potential as a powerful instrument for deciphering complex data sets, poised to drive revolutionary changes across diverse domains. QML’s applications are wide-ranging and impactful, including breakthroughs in drug discovery, large-scale stellar classification, natural language processing, recommendation systems, and generative learning models [20?–34] .  \nDespite its promising advantages and future, QML is still in its early development stages, due to numerous  \n∗ [d10245003@g.ntu.edu.tw](d10245003@g.ntu.edu.tw)[ ](d10245003@g.ntu.edu.tw)† [kuoenjui@umd.edu](kuoenjui@umd.edu)  \n‡ [min-hsiu.hsieh@foxconn.com](min-hsiu.hsieh@foxconn.com)  \n§ [goan@phys.ntu.edu.tw](goan@phys.ntu.edu.tw)  \nobstacles that must be overcome to realize its full potential and practicality. Critical challenges involve tackling the learnability [35–39] and trainability [40–44] of QML models. Beyond the learnability and trainability issues, QML in practice also presents a considerable hurdle. In scenarios where QML is solely utilized, gate angle encoding is a prevalent technique for input data processing. However, it becomes apparent that scaling issues arise; with increasing input data size, both the width and depth of the quantum circuit must expand accordingly, which can compromise accuracy in th","cbCaitsR2REarWd3","https://ap.wps.com/l/cbCaitsR2REarWd3","pdf",4378588,1,12,"English","en",105,"# Introduction\n## Quantum machine learning background and challenges\n## Practicality barriers in data encoding and inference\n# Quantum-Train contributions and experimental focus","[{\"question\":\"What problem does Quantum-Train (QT) target in hybrid quantum-classical machine learning?\",\"answer\":\"QT targets challenges in data encoding, model compression, and the hardware requirements needed during inference when quantum resources are limited.\"},{\"question\":\"How does QT reduce model parameters during training?\",\"answer\":\"QT uses a quantum neural network with a classical mapping model to reduce parameter count from M to O(polylog(M)) during training.\"},{\"question\":\"How is QT evaluated and what tasks does it support?\",\"answer\":\"Experiments demonstrate QT’s effectiveness on classification tasks, showing improvements in model efficiency and reduced generalization errors.\"}]","Quantum-Train - Rethinking Hybrid Quantum-Classical Machine Learning in the Model Compression Perspective | PDF",1785723757,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"quantum-train-rethinking-hybrid-quantum-classical-machine-learning-in-the-model-compression-perspective","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/quantum-train-rethinking-hybrid-quantum-classical-machine-learning-in-the-model-compression-perspective/119334/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does Quantum-Train (QT) target in hybrid quantum-classical machine learning?","Question",{"text":76,"@type":77},"QT targets challenges in data encoding, model compression, and the hardware requirements needed during inference when quantum resources are limited.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does QT reduce model parameters during training?",{"text":81,"@type":77},"QT uses a quantum neural network with a classical mapping model to reduce parameter count from M to O(polylog(M)) during training.",{"name":83,"@type":74,"acceptedAnswer":84},"How is QT evaluated and what tasks does it support?",{"text":85,"@type":77},"Experiments demonstrate QT’s effectiveness on classification tasks, showing improvements in model efficiency and reduced generalization errors.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":122},"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]