Noise-Robust Quantum Generative Models for Distribution Learning and Efficient Data Loading

Noise-Robust Quantum Generative Models for Distribution Learning and Efficient Data Loading | 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 Research Article Noise-Robust Quantum Generative Models for Distribution Learning and Efficient Data Loading Ankit Kumar Mandusia This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8001093/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Quantum machine learning offers powerful advantages in processing high-dimensional data, but loading classical probability distributions into quantum states remains a major challenge. This work extends quantum generative adversarial networks (qGANs) to overcome two critical limitations of early approaches: poor robustness to noise on near-term devices and limited capacity to model complex, multi-modal distributions. We introduce hybrid qGAN architectures that combine Wasserstein GAN with gradient penalty (WGAN-GP) and maximum mean discrepancy (MMD) losses with expressive quantum circuits, including quantum convolutional neural networks (QCNNs) and EfficientSU2 ansätze. Training is performed using seamless PyTorch–Qiskit integration, enabling stable optimization on both simulators and real quantum hardware.Experiments on 2D Gaussian and log-normal distributions—directly relevant to financial modeling—show faster convergence and higher fidelity than prior qGAN designs, with up to 80% lower Wasserstein distance under 5% depolarizing noise. The framework is further validated through European call option pricing via quantum amplitude estimation (QAE), achieving pricing errors below 1% on IBM’s 20-qubit superconducting systems. Theoretical analysis confirms gradient stability under noise, while empirical results include comprehensive noise sweeps, t-SNE latent space visualizations, and rigorous statistical tests (KL divergence, KS tests). This work establishes a practical path toward quantum advantage in generative modeling, with fully open-source code for reproducibility. quantum generative adversarial networks qGAN noise resilience distribution learning quantum data loading financial pricing Quantum Amplitude Estimation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted 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-8001093","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":546431110,"identity":"3eac9de3-fc63-4851-a933-fd10fd5b5bf0","order_by":0,"name":"Ankit Kumar Mandusia","email":"data:image/png;base64,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","orcid":"","institution":"Malaviya National Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Ankit","middleName":"Kumar","lastName":"Mandusia","suffix":""}],"badges":[],"createdAt":"2025-10-31 18:53:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8001093/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8001093/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96150698,"identity":"2384e637-6d88-42cf-91e2-b7e178371767","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3930,"visible":true,"origin":"","legend":"","description":"","filename":"dd8b2c5d42634a57b9ad55134f5befe6.json","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/21c4069839c47cd98beb0fbe.json"},{"id":96250869,"identity":"c375c939-708f-4442-bf48-858cdaf0e276","added_by":"auto","created_at":"2025-11-19 07:39:04","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":106610,"visible":true,"origin":"","legend":"","description":"","filename":"dd8b2c5d42634a57b9ad55134f5befe61enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/ca5a7dd704cfc7f69d759cc7.xml"},{"id":96150705,"identity":"470c935b-9480-4cea-a132-f8648af39195","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":58307,"visible":true,"origin":"","legend":"","description":"","filename":"CoverLetter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/7f5ba0a551fd78d3e9bb0565.pdf"},{"id":96150699,"identity":"464aace0-d571-4d44-a16f-2c39e92fa108","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2075925,"visible":true,"origin":"","legend":"","description":"","filename":"EnhanceQGanmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/d3d6d6c430208e1b477c5bf1.pdf"},{"id":96150701,"identity":"769f6c96-98cf-4456-a211-b4f643405bb3","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":65862,"visible":true,"origin":"","legend":"","description":"","filename":"FidelityvsNoisecurves.png","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/1ceb8c4c332ea28f5c233eeb.png"},{"id":96251615,"identity":"baaa5df7-4941-4638-a345-c0538ef761f8","added_by":"auto","created_at":"2025-11-19 07:39:50","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":84626,"visible":true,"origin":"","legend":"","description":"","filename":"classicalvsquantum.png","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/3777110b6077050c31383351.png"},{"id":96249396,"identity":"89b48fb5-863c-4d1e-afe9-19e40b9c0057","added_by":"auto","created_at":"2025-11-19 07:33:21","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":315096,"visible":true,"origin":"","legend":"","description":"","filename":"depthvsperformance.png","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/0d7407bda181e0037a4f56db.png"},{"id":96150707,"identity":"ab3c6d94-292b-4701-b738-a69c877cb42f","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":152229,"visible":true,"origin":"","legend":"","description":"","filename":"losscomparisonfixed.png","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/59fba955788b9603e68ec7ab.png"},{"id":96250745,"identity":"fa7ae3a7-5db8-4b33-80b4-f91955e426d0","added_by":"auto","created_at":"2025-11-19 07:38:56","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":163110,"visible":true,"origin":"","legend":"","description":"","filename":"lrsensitivityfixed.png","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/4e757a469902819b123ee132.png"},{"id":96150710,"identity":"dafff5de-02a0-4858-ae03-3daf26938037","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":445289,"visible":true,"origin":"","legend":"","description":"","filename":"noiseresil.png","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/6f576ef78401fe53e8dd7897.png"},{"id":96250575,"identity":"586dbac1-5514-42d9-b55b-c1205c0fb749","added_by":"auto","created_at":"2025-11-19 07:38:41","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81540,"visible":true,"origin":"","legend":"","description":"","filename":"pmfheatmaps.png","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/f3aa178b880f42cddbf77517.png"},{"id":96150715,"identity":"4e41a3ee-27fd-42f9-9469-192b28ccf71e","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":236269,"visible":true,"origin":"","legend":"","description":"","filename":"pricingconvergencecurves.png","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/0c97da9b488ccce1f0d9bad9.png"},{"id":96150709,"identity":"46bb648f-4707-44b8-8494-a216960d62b5","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"bst","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/76d82392625a3d9bd74be886.bst"},{"id":96150718,"identity":"411d59be-8e8f-4bde-aa90-97d5abfc543a","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"bst","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/5244f27d917b91d6a15fd03f.bst"},{"id":96251737,"identity":"893dcc30-412c-46d1-9d81-550725387689","added_by":"auto","created_at":"2025-11-19 07:39:59","extension":"bst","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/b7cc0c096ea5519c7789b99e.bst"},{"id":96251688,"identity":"31b4c3e5-2b65-4dbc-81b6-ff18dc2e5ca5","added_by":"auto","created_at":"2025-11-19 07:39:54","extension":"bst","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/200516ef57437ce3b9b1b4e0.bst"},{"id":96150704,"identity":"afcbd7c1-f8e9-4a4d-941e-cf137887ea95","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"cls","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/6b39979bb72ec700068ac53f.cls"},{"id":96250666,"identity":"1e6ddb9c-8912-4bb5-b1a9-e2b3131ffc6c","added_by":"auto","created_at":"2025-11-19 07:38:49","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/30cccfb1e27f9312e0704641.bst"},{"id":96248645,"identity":"374e23a7-3cdf-4b24-977a-6c56ec796feb","added_by":"auto","created_at":"2025-11-19 07:28:54","extension":"bst","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/bad47fcfccc73f32b4f43bde.bst"},{"id":96249843,"identity":"2ebf6fcc-e8d9-43eb-88fd-bd2620953251","added_by":"auto","created_at":"2025-11-19 07:36:25","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":230382,"visible":true,"origin":"","legend":"","description":"","filename":"tSNE.png","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/3795641fda2248e2d6e81148.png"},{"id":96150720,"identity":"70f1f6df-ee2d-461a-81f9-5fa7bbdfe3f2","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56964,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFidelityvsNoisecurves.png","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/b5d51fca389bd2de80abc63a.png"},{"id":96150712,"identity":"451dd6cf-813a-4c4a-84b8-9b6b78dd190c","added_by":"auto","created_at":"2025-11-18 07:26:11","extension":"xml","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":115758,"visible":true,"origin":"","legend":"","description":"","filename":"dd8b2c5d42634a57b9ad55134f5befe61structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/7cea1b69951c8f4ba7244f8f.xml"},{"id":96250496,"identity":"c0fb05bb-dd6c-4981-843a-8a23f4a48099","added_by":"auto","created_at":"2025-11-19 07:38:27","extension":"html","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":136133,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1/3b054e8683bd8a75b63ef1ee.html"},{"id":99797406,"identity":"22dfab80-3c8d-4d8e-8d82-34547f83f1db","added_by":"auto","created_at":"2026-01-08 13:45:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1826264,"visible":true,"origin":"","legend":"","description":"","filename":"EnhanceQGanmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8001093/v1_covered_a6244df3-3468-4288-80b1-871d289cf8e7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Noise-Robust Quantum Generative Models for Distribution Learning and Efficient Data Loading","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"quantum generative adversarial networks, qGAN, noise resilience, distribution learning, quantum data loading, financial pricing, Quantum Amplitude Estimation","lastPublishedDoi":"10.21203/rs.3.rs-8001093/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8001093/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eQuantum machine learning offers powerful advantages in processing high-dimensional data, but loading classical probability distributions into quantum states remains a major challenge. This work extends quantum generative adversarial networks (qGANs) to overcome two critical limitations of early approaches: poor robustness to noise on near-term devices and limited capacity to model complex, multi-modal distributions. We introduce hybrid qGAN architectures that combine Wasserstein GAN with gradient penalty (WGAN-GP) and maximum mean discrepancy (MMD) losses with expressive quantum circuits, including quantum convolutional neural networks (QCNNs) and EfficientSU2 ans\u0026auml;tze. Training is performed using seamless PyTorch\u0026ndash;Qiskit integration, enabling stable optimization on both simulators and real quantum hardware.Experiments on 2D Gaussian and log-normal distributions\u0026mdash;directly relevant to financial modeling\u0026mdash;show faster convergence and higher fidelity than prior qGAN designs, with up to 80% lower Wasserstein distance under 5% depolarizing noise. The framework is further validated through European call option pricing via quantum amplitude estimation (QAE), achieving pricing errors below 1% on IBM\u0026rsquo;s 20-qubit superconducting systems. Theoretical analysis confirms gradient stability under noise, while empirical results include comprehensive noise sweeps, t-SNE latent space visualizations, and rigorous statistical tests (KL divergence, KS tests). This work establishes a practical path toward quantum advantage in generative modeling, with fully open-source code for reproducibility.\u003c/p\u003e","manuscriptTitle":"Noise-Robust Quantum Generative Models for Distribution Learning and Efficient Data Loading","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-18 07:26:06","doi":"10.21203/rs.3.rs-8001093/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"88e32c4c-78ca-4712-bd6f-7eb8aa700227","owner":[],"postedDate":"November 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-07T13:09:34+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-18 07:26:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8001093","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8001093","identity":"rs-8001093","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}