[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-116865-en":3,"doc-seo-116865-105":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},116865,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Shadows of quantum machine learning","Quantum machine learning offers potential quantum advantages, yet practical deployment is constrained by the need to access a quantum computer for evaluating trained models on new data. A proposed solution inserts a shadowing phase after training: the quantum computer collects information that enables a classically computable approximation of the learned function. The work defines shadow models using quantum linear models together with classical shadow tomography, proving the existence of shadow models with provable quantum advantage over fully classical approaches under standard cryptographic assumptions, and showing limits where not all quantum models are efficiently shadowfiable.","Shadows of quantum machine learning  \narXiv :2306 .00061v1 [ quant-ph] 31 May 2023  \nSofiene Jerbi, 1, 2 Casper Gyurik,3 Simon C. Marshall,3 Riccardo Molteni,3 and Vedran Dunjko3  \n1 Institute for Theoretical Physics, University of Innsbruck, Austria  \n2 Dahlem Center for Complex Quantum Systems, Freie Universit¨at Berlin, Germany  \n3 applied Quantum algorithms (aQa), Leiden University, The Netherlands (Dated: June 2, 2023)  \nQuantum machine learning is often highlighted as one of the most promising uses for a quantum computer to solve practical problems. 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 toa quantum computer in order to be evaluated on new data. To solve this issue, we suggest that following the training phase of a quantum model, a quantum computer could be used to generate what we call a classical shadow of this model, i.e., a classically computable approximation of the learned function. While recent works already explore this idea and suggest approaches to construct such shadow models, they also raise the possibility that a completely classical model could be trained instead, thus circumventing the need for a quantum computer in the first place. In this work, we take a novel approach to define shadow models based on the frameworks of quantum linear models and classical shadow tomography. This approach allows us to show that there exist shadow models which can solve certain learning tasks that are intractable for fully classical models, based on widely-believed cryptography assumptions. We also discuss the (un)likeliness that all quantum models could be shadowfiable, based on common assumptions in complexity theory.  \nI. INTRODUCTION  \nQuantum machine learning is a rapidly growing field [1–3] driven by its potential to achieve quantum advantagesin 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 circuits [4–6] . Indeed, such quantum models have already been shown to achieve good learning performance in benchmarking tasks, both in numerical simulations [7–11] and on actual quantum hardware [12–15] . Moreover, based on widely-believed cryptography assumptions, these models also hold the promise to solve certain learning tasks that are intractable for classical algorithms [16, 17] .  \nDespite 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 classical shadows 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.  \nThe conceptual idea of generating shadows of quantum models was already proposed by Schreiber et al. [18], albeit under the terminology of classical surrogates. In that work, as well as in that of Landman et al. [19], the authors make use of the general expression of quantum models as trigonometric polynomials [20] to learn the Fourier representation of trained models and evaluate them classic","cbCaie9GEOF89gB1","https://ap.wps.com/l/cbCaie9GEOF89gB1","pdf",984270,1,23,"English","en",105,"# Introduction\n## Motivation: training vs deployment bottlenecks\n## Shadow models and classical surrogates\n## Open questions addressed\n## Paper approach and contributions","[{\"question\":\"What problem does the paper address in practical quantum machine learning deployment?\",\"answer\":\"Trained quantum machine learning models still require access to a quantum computer to be evaluated on new data during deployment, limiting real-world applicability due to scarcity of quantum resources.\"},{\"question\":\"How does the paper’s shadowing phase help deployment?\",\"answer\":\"After training, a quantum computer is used to collect information to construct a classically computable classical shadow of the learned function, allowing classical evaluation on new inputs.\"},{\"question\":\"What are the two main open questions the paper answers?\",\"answer\":\"Whether shadow models can provide a quantum advantage over fully classical models, and whether there exist quantum models that do not admit efficiently evaluatable classical shadows.\"}]","Shadows of quantum machine learning | PDF",1785672136,58,{"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/116865/",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 problem does the paper address in practical quantum machine learning deployment?","Question",{"text":76,"@type":77},"Trained quantum machine learning models still require access to a quantum computer to be evaluated on new data during deployment, limiting real-world applicability due to scarcity of quantum resources.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the paper’s shadowing phase help deployment?",{"text":81,"@type":77},"After training, a quantum computer is used to collect information to construct a classically computable classical shadow of the learned function, allowing classical evaluation on new inputs.",{"name":83,"@type":74,"acceptedAnswer":84},"What are the two main open questions the paper answers?",{"text":85,"@type":77},"Whether shadow models can provide a quantum advantage over fully classical models, and whether there exist quantum models that do not admit efficiently evaluatable classical shadows.","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},[94,98,102,106,111,116,121,124,129,132,136],{"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":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]