Quantum automated learning

Quantum automated learning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Quantum automated learning Dong-Ling Deng, Qi Ye, Shuangyue Geng, Zizhao Han, Weikang Li, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8054206/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Machine learning is widely believed to be a promising practical application of quantum computing. Existing quantum machine learning schemes typically employ a quantum-classical hybrid approach that relies crucially on gradients of model parameters. Such an approach lacks provable convergence to global minima and will become infeasible as quantum learning models scale up. Here, we introduce quantum automated learning, where no variational parameter is involved and the training process is converted to quantum state preparation. In particular, we encode training data into unitary operations and iteratively evolve a random initial state under these unitaries and their inverses, with a target-oriented perturbation towards higher prediction accuracy sandwiched in between. Under rea- sonable assumptions, we rigorously prove that the evolution converges exponentially to the desired state corresponding to the global minimum of the loss function. We show that such a training process can be understood from the perspective of preparing quantum states by imaginary time evolution, where the data-encoded unitaries together with target-oriented perturbations would train the quantum learning model in an automated fashion. We further prove that the introduced quantum automated learning paradigm features universal representation power and good generalization ability with the generalization error upper bounded by the ratio between a logarithmic function of the Hilbert space dimension and the number of training samples. In addition, we carry out extensive numerical simulations on real-life images and quantum data to demonstrate the effectiveness of our approach and validate the assumptions. Our results establish an unconventional quantum learning strategy that is gradient-free with provable and explainable trainability, which would be crucial computing in machine learning scenarios. Physical sciences/Physics/Quantum physics/Quantum information Physical sciences/Mathematics and computing/Computer science Full Text Additional Declarations There is NO Competing Interest. L.-M.D. hold shares with HYQ Co. Supplementary Files supp.pdf Supplementary Information for: Quantum automated learning Cite Share Download PDF Status: Under Review Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8054206","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":553526330,"identity":"0c1f71ec-1bca-4d48-9716-25d21ef6274c","order_by":0,"name":"Dong-Ling Deng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8klEQVRIiWNgGAWjYDCC4wwGQNKGgYEZjEAggYCWw2AtaRIkazksAWITp4XvMPPGxwW/ztfJt/Mefl3YZsfAz55jwPBzB24tkofZio1n9t2WMDjMl2Y9sy2ZQbLnjQFj7xncWgwO85hJ8/YAtTDzmBnztjEzGNzIMWBmbMOrxfw3b885CflmsJZ6BnsitJgx8/w4IMFwmMf4MW8bMDQkCGgB+UWatyFZcgNY77njPBJnnhUc7MWjhe9488bPPH/s+OX7zxh/5imrluNvT9744CceLWAAdQYbKHJ4QKwDBDQAwR8wyfyBsMpRMApGwSgYiQAAP2xKF4Lm3J8AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-1042-4646","institution":"Tsinghua University","correspondingAuthor":true,"prefix":"","firstName":"Dong-Ling","middleName":"","lastName":"Deng","suffix":""},{"id":553526331,"identity":"8e879ab2-7071-44f7-a1a3-b20e66582b7c","order_by":1,"name":"Qi Ye","email":"","orcid":"","institution":"Tsinghua University","correspondingAuthor":false,"prefix":"","firstName":"Qi","middleName":"","lastName":"Ye","suffix":""},{"id":553526332,"identity":"09151202-3e61-4396-b920-027f9d13b6d3","order_by":2,"name":"Shuangyue Geng","email":"","orcid":"https://orcid.org/0009-0008-8212-7633","institution":"Tsinghua University","correspondingAuthor":false,"prefix":"","firstName":"Shuangyue","middleName":"","lastName":"Geng","suffix":""},{"id":553526333,"identity":"3dcfe3c4-efdc-4df9-8913-f4ac1998d93b","order_by":3,"name":"Zizhao Han","email":"","orcid":"","institution":"Tsinghua University","correspondingAuthor":false,"prefix":"","firstName":"Zizhao","middleName":"","lastName":"Han","suffix":""},{"id":553526334,"identity":"cf700248-f4b9-42f7-8a06-6f1a470c7195","order_by":4,"name":"Weikang Li","email":"","orcid":"https://orcid.org/0000-0002-7137-5390","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Weikang","middleName":"","lastName":"Li","suffix":""},{"id":553526335,"identity":"ac098a5b-0b94-4fd7-9cf1-c91a5bbbbca7","order_by":5,"name":"Lu-Ming Duan","email":"","orcid":"https://orcid.org/0000-0002-5539-2721","institution":"Tsinghua University","correspondingAuthor":false,"prefix":"","firstName":"Lu-Ming","middleName":"","lastName":"Duan","suffix":""}],"badges":[],"createdAt":"2025-11-07 07:25:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8054206/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8054206/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97263390,"identity":"4f96eafb-d1d0-403e-9fad-0a02a0fe8f94","added_by":"auto","created_at":"2025-12-02 14:19:35","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1679984,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8054206/v1/6e1e492a950df740215238b7.pdf"},{"id":97263389,"identity":"e056499a-85c6-4895-8f30-5f3225f11b23","added_by":"auto","created_at":"2025-12-02 14:19:34","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7900,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS2589844.json","url":"https://assets-eu.researchsquare.com/files/rs-8054206/v1/5c69c7e84f4978d3b1fc42b1.json"},{"id":97367720,"identity":"f119196b-471f-4873-aba1-75a3e79839ff","added_by":"auto","created_at":"2025-12-03 16:20:27","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":453064,"visible":true,"origin":"","legend":"","description":"","filename":"supp.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8054206/v1/b95ae408515187cfbb802e0c.pdf"},{"id":97372874,"identity":"fc7ae651-b78b-42c7-95f6-89c04ea9121d","added_by":"auto","created_at":"2025-12-03 16:33:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1388544,"visible":true,"origin":"","legend":"Article File","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8054206/v1_covered_b7db9e44-edfc-486d-979b-42f484ca5783.pdf"},{"id":97263391,"identity":"99beb762-9f58-4a14-8254-e2a21359b51c","added_by":"auto","created_at":"2025-12-02 14:19:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":453064,"visible":true,"origin":"","legend":"Supplementary Information for: Quantum automated learning","description":"","filename":"supp.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8054206/v1/760d1f6bfd449443d09dca9f.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.\nL.-M.D. hold shares with HYQ Co.","formattedTitle":"Quantum automated learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8054206/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8054206/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Machine learning is widely believed to be a promising practical application of quantum computing. Existing quantum machine learning schemes typically employ a quantum-classical hybrid approach that relies crucially on gradients of model parameters. Such an approach lacks provable convergence to global minima and will become infeasible as quantum learning models scale up. Here, we introduce quantum automated learning, where no variational parameter is involved and the training process is converted to quantum state preparation. In particular, we encode training data into unitary operations and iteratively evolve a random initial state under these unitaries and their inverses, with a target-oriented perturbation towards higher prediction accuracy sandwiched in between. Under rea- sonable assumptions, we rigorously prove that the evolution converges exponentially to the desired state corresponding to the global minimum of the loss function. We show that such a training process can be understood from the perspective of preparing quantum states by imaginary time evolution, where the data-encoded unitaries together with target-oriented perturbations would train the quantum learning model in an automated fashion. We further prove that the introduced quantum automated learning paradigm features universal representation power and good generalization ability with the generalization error upper bounded by the ratio between a logarithmic function of the Hilbert space dimension and the number of training samples. In addition, we carry out extensive numerical simulations on real-life images and quantum data to demonstrate the effectiveness of our approach and validate the assumptions. Our results establish an unconventional quantum learning strategy that is gradient-free with provable and explainable trainability, which would be crucial computing in machine learning scenarios.","manuscriptTitle":"Quantum automated learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-02 14:19:30","doi":"10.21203/rs.3.rs-8054206/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"ecae3f78-e40c-44e5-b03a-e0c97a56db51","owner":[],"postedDate":"December 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":58899810,"name":"Physical sciences/Physics/Quantum physics/Quantum information"},{"id":58899811,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2026-05-13T21:10:50+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-02 14:19:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8054206","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8054206","identity":"rs-8054206","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}