[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117124-en":3,"doc-seo-117124-105":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},117124,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Shadows of Quantum Machine Learning","Quantum machine learning holds promise for practical quantum advantages, yet deployed models usually require access to a quantum computer for evaluation on new data. This work introduces quantum models whose quantum resources are confined to training, while deployment uses a classical evaluation process. The training phase produces a generated “shadow model” that enables classical representation of the trained quantum state for computing model outputs. The authors prove universality for classically deployed quantum ML, quantify reduced learning capacities versus fully quantum models, and establish a conditional provable learning advantage over fully classical learners under complexity-theoretic assumptions.","|  |  |  |  |\n| --- | --- | --- | --- |\n| Article [https://doi.org/10.1038/s41467-024-49877-8](https://doi.org/10.1038/s41467-024-49877-8) |  |  |  |\n| Shadows of quantum machine learning |  |  |  |\n| Received: 9 May 2024\u003Cbr>Accepted: 21 June 2024 Check for updates | Sofiene Jerbi1,2 , Casper Gyurik3, Simon C. Marshall3, Riccardo Molteni3 & Vedran Dunjko 3\u003Cbr>Quantum machine learning is often highlighted as one of the most promising practical applications for which quantum computers could provide a computational advantage. However, a major obstacle to the widespread use of quantum machine learning models in practice is that these models, even once trained, still require access to a quantum computer in order to be evaluated on new data. To solve this issue, we introduce a class of quantum models where quantum resources are only required during training, while the deployment of the trained model is classical. Specifically, the training phase of our models ends with the generation of a ‘shadow model’ from which the classical deployment becomes possible. We prove that: (i) this class of models is universal for classically-deployed quantum machine learning; (ii) it does have restricted learning capacities compared to ‘fully quantum’ models, but nonetheless (iii) it achieves a provable learning advantage over fully classical learners, contingent on widely believed assumptions in complexity theory. These results provide compelling evidence that quantum machine learning can confer learning advantages across a substantially broader range of scenarios, where quantum computers are exclusively employed during the training phase. By enabling classical deployment, our approach facilitates the implementation of quantum machine learning models in various practical contexts. |  |  |\n| Quantum machine learning is a rapidly growing field1–3 driven by its potential to achieve quantum advantages in practical applications. A particularly interesting approach to make quantum machine learning applicable in the near term is to develop learning models based on parametrized quantum circuits4–6. Indeed, such quantum models have already been shown to achieve good learning performance in benchmarking tasks, both in numerical simulations7–11 and on actual quantum hardware12–15. Moreover, based on widely believed cryptography assumptions, these models also hold the promise to solve certain learning tasks that are intractable for classical algorithms16,17, including predicting ground state properties of highly-interacting quantum systems18.\u003Cbr>Despite these advances, quantum machine learning is facing a major obstacle for its use in practice. A typical workflow of a machine learning model involved, e.g., in driving autonomous vehicles, is divided into:(i)a training phase, where the model is trained, typically using training data or by reinforcement; followed by(ii) a deployment phase, |  | where the trained model is evaluated on new input data. For quantum machine learning models, both of these phases require access to a quantum computer. But given that in many practical machine learning applications, the trained model is meant for a widespread deployment, the current scarcity of quantum computing access dramatically reduces the applicability of quantum machine learning. One way of addressing this problem is by generating shadow models out of quantum machine learning models. That is, we propose inserting a shadowing phase between the training and deployment, where a quantum computer is used to collect information on the quantum model. Then a classical computer can use this information to evaluate the model on new data during the deployment phase.\u003Cbr>The conceptual idea of generating shadows of quantum models was already proposed by Schreiber et al.19, albeit under the terminology of classical surrogates. In that work, as well as in that of Landmanet al.20, the authors make use of the general expression of quantum models as trigonometric polynomials21 to learn the","cbCair19t31UK4dA","https://ap.wps.com/l/cbCair19t31UK4dA","pdf",702425,1,7,"English","en",105,"# Background and Motivation\n## Quantum machine learning workflow and deployment bottleneck\n## Parametrized quantum circuits and prior progress\n# Shadow Models for Classical Deployment\n## Training-time quantum resources only\n## Shadowing phase and classical evaluation\n## Relation to shadow tomography and prior surrogates\n# Results and Theoretical Guarantees\n## Universality for classically deployed quantum ML\n## Restricted capacities vs fully quantum models\n## Provable learning advantage over classical learners","[{\"question\":\"What is the main practical obstacle for quantum machine learning deployment?\",\"answer\":\"Even after training, quantum machine learning models typically need quantum computer access to be evaluated on new data during deployment.\"},{\"question\":\"How do “shadow models” address the deployment bottleneck?\",\"answer\":\"They insert a shadowing phase between training and deployment, using quantum circuits to generate information that a classical algorithm can use to evaluate the trained model on new inputs.\"},{\"question\":\"What guarantees does the paper provide about the proposed class of models?\",\"answer\":\"The authors prove the approach is universal for classically deployed quantum ML, has restricted learning capacities compared to fully quantum models, yet still achieves a provable learning advantage over fully classical learners under widely believed complexity-theory assumptions.\"}]","Shadows of Quantum Machine Learning | PDF",1785674006,18,{"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},"shadows-of-quantum-machine-learning","",{"@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/shadows-of-quantum-machine-learning/117124/",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","2026-08-05","2026-08-02",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 is the main practical obstacle for quantum machine learning deployment?","Question",{"text":76,"@type":77},"Even after training, quantum machine learning models typically need quantum computer access to be evaluated on new data during deployment.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How do “shadow models” address the deployment bottleneck?",{"text":81,"@type":77},"They insert a shadowing phase between training and deployment, using quantum circuits to generate information that a classical algorithm can use to evaluate the trained model on new inputs.",{"name":83,"@type":74,"acceptedAnswer":84},"What guarantees does the paper provide about the proposed class of models?",{"text":85,"@type":77},"The authors prove the approach is universal for classically deployed quantum ML, has restricted learning capacities compared to fully quantum models, yet still achieves a provable learning advantage over fully classical learners under widely believed complexity-theory assumptions.","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},[94,98,102,106,111,116,120,123,128,131,135],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"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"]