[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118418-en":3,"doc-seo-118418-105":30,"detail-sidebar-cat-0-en-105":95},{"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":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},118418,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Single-shot quantum machine learning - Quantum learning near-deterministic prediction","Quantum machine learning uses quantum computers to enhance learning methods, but prediction is often costly because quantum measurements are inherently probabilistic. This work analyzes when quantum learning models can avoid repeated executions and yield near-deterministic predictions through single-shot operation. A rigorous definition of single-shot quantum classifiers is provided, linking near-determinism to the distinguishability of embedded quantum states. For circuit-based embeddings, a minimum circuit depth is required, and models cannot generally be single-shot while remaining trainable.","Single-shot quantum machine learning  \narXiv :2406 . 13812v1 [ quant-ph] 19 Jun 2024  \nErik Recio-Armengol, 1, 2 Jens Eisert,3, 4, 5 and Johannes Jakob Meyer3  \n1 ICFO-Institut de Ciencies Fotoniques, The Barcelona Institute of  \nScience and Technology, 08860 Castelldefels (Barcelona), Spain  \n2 Eurecat, Centre Tecnol`ogic de Catalunya, Multimedia Technologies, 08005 Barcelona, Spain  \n3 Dahlem Center for Complex Quantum Systems, Freie Universit¨at Berlin, 14195 Berlin, Germany  \n4 Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany  \n5 Helmholtz-Zentrum Berlin f¨ur Materialien und Energie, 14109 Berlin, Germany (Dated: June 21, 2024)  \nQuantum machine learning aims to improve learning methods through the use of quantum computers. If it is to ever realize its potential, many obstacles need to be overcome. A particularly pressing one arises at the prediction stage because the outputs of quantum learning models are inherently random. This creates an often considerable overhead, as many executions of a quantum learning model have to be aggregated to obtain an actual prediction. In this work, we analyze when quantum learning models can evade this issue and produce predictions in a near-deterministic way – paving the way to single-shot quantum machine learning. We give a rigorous definition of single-shotness in quantum classifiers and show that the degree to which a quantum learning model is near-deterministic is constrained by the distinguishability of the embedded quantum states used in the model. Opening the black box of the embedding, we show that if the embedding is realized by quantum circuits, a certain depth is necessary for single-shotness to be even possible. We conclude by showing that quantum learning models cannot be single-shot in a generic way and trainable atthe same time.  \nMachine learning is a burgeoning field where rapid advances regularly overturn assumptions on what can and cannot be learned by classical computers. This ongoing success story spurs interest in quantum machine learning, its intersection with quantum computing, another field that has seen tremendous technical progress recently. Investigating if quantum computers can be used to construct learning models that somehow outperform their classical counterparts has become one of the principal avenues of research in quantum machine learning.  \nWhile the intrinsic quantum nature of such models gives them at least some theoretical potential to push beyond the boundary of what is classically possible [1– 4], it also comes with inherent downsides. Previous research in that direction mostly focused on the training stage, where issues like barren plateaus [5] complicate the optimization of quantum learning models. Issues do, however, also appear at the inference stage, i.e. when a prediction is to be produced by a quantum learning model. A quantum learning model that deserves that name needs to perform some sort of manipulation of a quantum system. To extract a classical label, however, a measurement needs to be performed. It is the nature of quantum mechanics that the outcomes of such measurements are inherently probabilistic. For the model to solve a learning problem, for example to correctly classify an image, the output needs to be deterministic. In practice, a quantum learning model is run a large number of times to circumvent the probabilistic outcomes of measurements and to extract a prediction, [e.g. in](e.g. in) the form of an expectation value of a suitably chosen observable. This issue, an instance of what has been called the measurement problem, even persists if the model is run on a fault-tolerant quantum computer.  \nFigure 1 . A depiction of the intuitive difference between a regular quantum classifier (top panel) and a single-shot one (bottom panel) . In both cases, data is embedded into a quantum system through a quantum feature map. In a regular classifier, the procedure that extracts the label has to be repeated often and then aggrega","cbCaihAo8IvJ6k7A","https://ap.wps.com/l/cbCaihAo8IvJ6k7A","pdf",647070,1,18,"English","en",105,"# Introduction\n## Motivation: measurement-induced overhead in quantum inference\n## Single-shotness problem and near-deterministic prediction\n# Single-shot quantum classifiers\n## Rigorous definition and role of embedded state distinguishability\n## Connection to quantum hypothesis testing\n# Circuit depth requirements\n## Noise-free vs noisy embeddings\n# Limits and trainability trade-offs\n## Generic single-shotness vs expressivity","[{\"question\":\"Why does quantum machine learning often require many runs during inference?\",\"answer\":\"Quantum classifiers must measure a quantum system to obtain classical labels, and measurement outcomes are inherently probabilistic. Many executions are aggregated (e.g., via majority vote or expectation values) to produce a reliable prediction.\"},{\"question\":\"What does “single-shot quantum learning” mean in this work?\",\"answer\":\"It defines single-shotness as producing near-deterministic predictions from essentially one pass through the quantum model. The paper provides a rigorous criterion for when this property holds in quantum classifiers.\"},{\"question\":\"What determines how near-deterministic a single-shot quantum classifier can be?\",\"answer\":\"The degree of near-determinism is constrained by the distinguishability of the embedded quantum states used in the feature map of the model.\"},{\"question\":\"Are single-shot quantum learning models always possible and easy to train?\",\"answer\":\"No. The paper concludes that quantum learning models cannot be single-shot in a generic way while also being trainable, because models with the single-shot property tend to be overly expressive.\"}]","Single-shot quantum machine learning - Quantum learning near-deterministic prediction | PDF",1785683519,45,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"single-shot-quantum-machine-learning-quantum-learning-near-deterministic-prediction","",{"@graph":36,"@context":89},[37,54,68],{"@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/single-shot-quantum-machine-learning-quantum-learning-near-deterministic-prediction/118418/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"Why does quantum machine learning often require many runs during inference?","Question",{"text":75,"@type":76},"Quantum classifiers must measure a quantum system to obtain classical labels, and measurement outcomes are inherently probabilistic. Many executions are aggregated (e.g., via majority vote or expectation values) to produce a reliable prediction.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does “single-shot quantum learning” mean in this work?",{"text":80,"@type":76},"It defines single-shotness as producing near-deterministic predictions from essentially one pass through the quantum model. The paper provides a rigorous criterion for when this property holds in quantum classifiers.",{"name":82,"@type":73,"acceptedAnswer":83},"What determines how near-deterministic a single-shot quantum classifier can be?",{"text":84,"@type":76},"The degree of near-determinism is constrained by the distinguishability of the embedded quantum states used in the feature map of the model.",{"name":86,"@type":73,"acceptedAnswer":87},"Are single-shot quantum learning models always possible and easy to train?",{"text":88,"@type":76},"No. The paper concludes that quantum learning models cannot be single-shot in a generic way while also being trainable, because models with the single-shot property tend to be overly expressive.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]