[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123464-en":3,"doc-seo-123464-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},123464,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Can Geometric Quantum Machine Learning Lead to Advantage in Barcode Classification?","The work studies how to distinguish two vectors, represented as images or barcodes, and to learn whether they are related. It introduces a geometric quantum machine learning (GQML) method that embeds symmetries to classify similar versus dissimilar pairs using global correlations. The approach adapts measurements in a symmetry-aware way and targets few-shot generalization. Benchmarks against Siamese classical deep neural networks and convolutional models show quantum networks outperform classical baselines, supported by an analysis of correlated data distributions and connections to known quantum-classical separation results.","Can Geometric Quantum Machine Learning Lead to Advantage in Barcode Classification?  \narXiv :2409 .01496v1 [ quant-ph] 2 Sep 2024  \nChukwudubem Umeano, Stefano Scali, and Oleksandr Kyriienko  \nDepartment of Physics and Astronomy, University of Exeter, Stocker Road, Exeter EX4 4QL, United Kingdom  \n(Dated: September 4, 2024)  \nWe consider the problem of distinguishing two vectors (visualized as images or barcodes) and learning if they are related to one another. For this, we develop a geometric quantum machine learning (GQML) approach with embedded symmetries that allows for the classification of similar and dissimilar pairs based on global correlations, and enables generalization from just a few samples. Unlike GQML algorithms developed to date, we propose to focus on symmetry-aware measurement adaptation that outperforms unitary parametrizations. We compare GQML for similarity testing against classical deep neural networks and convolutional neural networks with Siamese architectures. We show that quantum networks largely outperform their classical counterparts. We explain this difference in performance by analyzing correlated distributions used for composing our dataset. We relate the similarity testing with problems that showcase a proven maximal separation between the BQP complexity class and the polynomial hierarchy. While the ability to achieve advantage largely depends on how data are loaded, we discuss how similar problems can benefit from quantum machine learning.  \nIntroduction.— Machine learning (ML) became a crucial tool for information processing [1], bringing us closer to advanced artificial intelligence [2, 3] . Its further progress largely depends on the development of qualitatively new hardware for computing and algorithmic breakthroughs [4] . From this perspective, quantum machine learning (QML) [5]—an area of ML devoted to developing quantum computing algorithms to solve learning-based problems—has attracted much attention in recent years [6–8] . Generally motivated by the capability of quantum computers of getting a superpolynomial improvement in scaling as compared to classical algorithms [9–11], QML has evolved both in terms of applications to be considered, and approaches to be used. Notably, the adoption of variational quantum algorithms (VQAs) [12, 13] led to the variety of quantum circuit optimization-based protocols, applied to tasks such as classification [7, 14–18], phase recognition [19–21], generative modeling [22–28], and physics-informed solving of differential equations [29–34], showing potential in areas where classical methods struggle. A distinct set of tools has been developed for embedding data into quantum computers [35–37], including various feature maps designed to exploit the high-dimensional space of quantum states for enhanced data representation and processing efficiency [38– 44] . The use-cases of QML include image recognition [45– 48], data analysis in high-energy physics [49–53], financial risk assessment [21, 54, 55], fraud detection [56–59], natural language processing [60–62], graph-based learning [63–66], power flow analysis [67], enhanced molecular simulations in chemistry [68], among many others.  \nSeveral open questions are yet to be answered before QML delivers its full promise. First, we need to decide how to parameterize quantum models in the most advantageous way. Do we get an advantage from training variational circuits, or is quantum embedding enough [69]? Or shall we use the structure of quantum kernels [70–72]? Second, we still need to understand where a proven advantage in quantum machine learning can come from [73] . Does it mainly concern improving runtime and circuit depth [6, 74, 75]? Does it come from sampling (generative modelling) [26, 76–78], or do we gain from better generalization of quantum models [19, 79–82]?  \nOne idea fuelling efficient quantum models leans on us-  \ning symmetries of considered datasets and problems [83– 85] . This approach, inspired","cbCaiuv86u7I8K1U","https://ap.wps.com/l/cbCaiuv86u7I8K1U","pdf",652952,1,"English","en",105,"# Introduction\n## Open questions in quantum machine learning\n## Geometric quantum machine learning and symmetries\n## Quantum-classical separation and provable advantages","[{\"question\":\"What problem does the document address for barcode classification?\",\"answer\":\"It targets similarity testing: distinguishing whether two barcodes (visualized as vectors/images) are correlated or uncorrelated and learning this relationship for classification.\"},{\"question\":\"How does the proposed GQML approach differ from prior quantum ML methods?\",\"answer\":\"It emphasizes symmetry-aware measurement adaptation rather than focusing on unitary parametrizations, aiming for better performance and few-sample generalization.\"},{\"question\":\"Which models are used for comparison, and what is the outcome?\",\"answer\":\"The quantum approach is compared with classical Siamese deep neural networks and convolutional neural networks. The document reports that quantum networks outperform their classical counterparts for the considered dataset settings.\"}]","Can Geometric Quantum Machine Learning Lead to Advantage in Barcode Classification? | PDF",1785816660,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"can-geometric-quantum-machine-learning-lead-to-advantage-in-barcode-classification","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/can-geometric-quantum-machine-learning-lead-to-advantage-in-barcode-classification/123464/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the document address for barcode classification?","Question",{"text":74,"@type":75},"It targets similarity testing: distinguishing whether two barcodes (visualized as vectors/images) are correlated or uncorrelated and learning this relationship for classification.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the proposed GQML approach differ from prior quantum ML methods?",{"text":79,"@type":75},"It emphasizes symmetry-aware measurement adaptation rather than focusing on unitary parametrizations, aiming for better performance and few-sample generalization.",{"name":81,"@type":72,"acceptedAnswer":82},"Which models are used for comparison, and what is the outcome?",{"text":83,"@type":75},"The quantum approach is compared with classical Siamese deep neural networks and convolutional neural networks. The document reports that quantum networks outperform their classical counterparts for the considered dataset settings.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]