{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:19:23Z","timestamp":1777490363471,"version":"3.51.4"},"reference-count":41,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T00:00:00Z","timestamp":1693353600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T00:00:00Z","timestamp":1693353600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Quantum machine learning has become an area of growing interest but has certain theoretical and hardware-specific limitations. Notably, the problem of vanishing gradients, or barren plateaus, renders the training impossible for circuits with high qubit counts, imposing a limit on the number of qubits that data scientists can use for solving problems. Independently, angle-embedded supervised quantum neural networks were shown to produce truncated Fourier series with a degree directly dependent on two factors: the depth of the encoding and the number of parallel qubits the encoding applied to. The degree of the Fourier series limits the model expressivity. This work introduces two new architectures whose Fourier degrees grow exponentially: the sequential and parallel exponential quantum machine learning architectures. This is done by efficiently using the available Hilbert space when encoding, increasing the expressivity of the quantum encoding. Therefore, the exponential growth allows staying at the low-qubit limit to create highly expressive circuits avoiding barren plateaus. Practically, parallel exponential architecture was shown to outperform the existing linear architectures by reducing their final mean square error value by up to 44.7% in a one-dimensional test problem. Furthermore, the feasibility of this technique was also shown on a trapped ion quantum processing unit.<\/jats:p>","DOI":"10.1088\/2632-2153\/ace757","type":"journal-article","created":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T22:33:21Z","timestamp":1689287601000},"page":"035036","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["An exponentially-growing family of universal quantum circuits"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3150-5397","authenticated-orcid":false,"given":"Mo","family":"Kordzanganeh","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8455-020X","authenticated-orcid":false,"given":"Pavel","family":"Sekatski","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0354-2457","authenticated-orcid":false,"given":"Leonid","family":"Fedichkin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5033-4063","authenticated-orcid":true,"given":"Alexey","family":"Melnikov","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,8,30]]},"reference":[{"key":"mlstace757bib1","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/nature23474","article-title":"Quantum machine learning","volume":"549","author":"Biamonte","year":"2017","journal-title":"Nature"},{"key":"mlstace757bib2","doi-asserted-by":"publisher","DOI":"10.1080\/23746149.2023.2165452","article-title":"Quantum machine learning: from physics to software engineering","volume":"8","author":"Melnikov","year":"2023","journal-title":"Adv. Phys. X"},{"key":"mlstace757bib3","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1038\/s43588-021-00084-1","article-title":"The power of quantum neural networks","volume":"1","author":"Abbas","year":"2021","journal-title":"Nat. Comput. Sci."},{"key":"mlstace757bib4","article-title":"Practical application-specific advantage through hybrid quantum computing","author":"Perelshtein","year":"2022"},{"key":"mlstace757bib5","doi-asserted-by":"crossref","DOI":"10.34133\/icomputing.0028","article-title":"Parallel hybrid networks: an interplay between quantum and classical neural networks","author":"Kordzanganeh","year":"2023"},{"key":"mlstace757bib6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-14876-6","article-title":"Review of some existing QML frameworks and novel hybrid classical\u2013quantum neural networks realising binary classification for the noisy datasets","volume":"12","author":"Schetakis","year":"2022","journal-title":"Sci. Rep."},{"key":"mlstace757bib7","article-title":"Quantum machine learning for image classification","author":"Senokosov","year":"2023"},{"key":"mlstace757bib8","article-title":"Hyperparameter optimization of hybrid quantum neural networks for car classification","author":"Sagingalieva","year":"2022"},{"key":"mlstace757bib9","doi-asserted-by":"publisher","first-page":"2705","DOI":"10.3390\/cancers15102705","article-title":"Hybrid quantum neural network for drug response prediction","volume":"15","author":"Sagingalieva","year":"2023","journal-title":"Cancers"},{"key":"mlstace757bib10","doi-asserted-by":"publisher","first-page":"7062","DOI":"10.1109\/JSTARS.2023.3287154","article-title":"Quantum algorithms applied to satellite mission planning for Earth observation","volume":"16","author":"Rainjonneau","year":"2023","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"mlstace757bib11","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.3.030101","article-title":"Is quantum advantage the right goal for quantum machine learning?","volume":"3","author":"Schuld","year":"2022","journal-title":"PRX Quantum"},{"key":"mlstace757bib12","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.103.150502","article-title":"Quantum algorithm for linear systems of equations","volume":"103","author":"Harrow","year":"2009","journal-title":"Phys. Rev. Lett."},{"key":"mlstace757bib13","doi-asserted-by":"publisher","first-page":"4213","DOI":"10.1038\/ncomms5213","article-title":"A variational eigenvalue solver on a photonic quantum processor","volume":"5","author":"Peruzzo","year":"2014","journal-title":"Nat. Commun."},{"key":"mlstace757bib14","article-title":"Mathematical foundations for a compositional distributional model of meaning","author":"Coecke","year":"2010"},{"key":"mlstace757bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.103.032430","article-title":"Effect of data encoding on the expressive power of variational quantum-machine-learning models","volume":"103","author":"Schuld","year":"2021","journal-title":"Phys. Rev. A"},{"key":"mlstace757bib16","doi-asserted-by":"publisher","first-page":"226","DOI":"10.22331\/q-2020-02-06-226","article-title":"Data re-uploading for a universal quantum classifier","volume":"4","author":"n P\u00e9rez-Salinas","year":"2020","journal-title":"Quantum"},{"key":"mlstace757bib17","article-title":"Quantum machine learning for radio astronomy","author":"Kordzanganeh","year":"2021"},{"key":"mlstace757bib18","doi-asserted-by":"publisher","first-page":"6961","DOI":"10.1038\/s41467-021-27045-6","article-title":"Noise-induced barren plateaus in variational quantum algorithms","volume":"12","author":"Wang","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstace757bib19","doi-asserted-by":"publisher","DOI":"10.1063\/1.3672064","article-title":"Composite parameterization and Haar measure for all unitary and special unitary groups","volume":"53","author":"Spengler","year":"2012","journal-title":"J. Math. Phys."},{"key":"mlstace757bib20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.99.032331","article-title":"Evaluating analytic gradients on quantum hardware","volume":"99","author":"Schuld","year":"2019","journal-title":"Phys. Rev. A"},{"key":"mlstace757bib21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.80.012304","article-title":"Exact and approximate unitary 2-designs and their application to fidelity estimation","volume":"80","author":"Dankert","year":"2009","journal-title":"Phys. Rev. A"},{"key":"mlstace757bib22","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s00220-009-0873-6","article-title":"Random quantum circuits are approximate 2-designs","volume":"291","author":"Harrow","year":"2009","journal-title":"Commun. Math. Phys."},{"key":"mlstace757bib23","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/CCC.2007.26","article-title":"Quantum t-designs: t-wise independence in the quantum world","author":"Ambainis","year":"2007"},{"key":"mlstace757bib24","doi-asserted-by":"publisher","first-page":"4812","DOI":"10.1038\/s41467-018-07090-4","article-title":"Barren plateaus in quantum neural network training landscapes","volume":"9","author":"McClean","year":"2018","journal-title":"Nat. Commun."},{"key":"mlstace757bib25","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s42484-020-00036-4","article-title":"Layerwise learning for quantum neural networks","volume":"3","author":"Skolik","year":"2021","journal-title":"Quantum Mach. Intell."},{"key":"mlstace757bib26","doi-asserted-by":"publisher","first-page":"214","DOI":"10.22331\/q-2019-12-09-214","article-title":"An initialization strategy for addressing barren plateaus in parametrized quantum circuits","volume":"3","author":"Grant","year":"2019","journal-title":"Quantum"},{"key":"mlstace757bib27","doi-asserted-by":"publisher","first-page":"1791","DOI":"10.1038\/s41467-021-21728-w","article-title":"Cost function dependent barren plateaus in shallow parametrized quantum circuits","volume":"12","author":"Cerezo","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstace757bib28","doi-asserted-by":"publisher","first-page":"466","DOI":"10.22331\/q-2021-06-04-466","article-title":"Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus","volume":"5","author":"Zhao","year":"2021","journal-title":"Quantum"},{"key":"mlstace757bib29","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/13\/4\/043016","article-title":"Interacting quantum observables: categorical algebra and diagrammatics","volume":"13","author":"Coecke","year":"2011","journal-title":"New J. Phys."},{"key":"mlstace757bib30","first-page":"12144","article-title":"Exponentially many local minima in quantum neural networks","author":"You","year":"2021","edition":"ed"},{"key":"mlstace757bib31","doi-asserted-by":"publisher","first-page":"7760","DOI":"10.1038\/s41467-022-35364-5","article-title":"Quantum variational algorithms are swamped with traps","volume":"13","author":"Anschuetz","year":"2022","journal-title":"Nat. Commun."},{"key":"mlstace757bib32","article-title":"Supervised quantum machine learning models are kernel methods","author":"Schuld","year":"2021"},{"key":"mlstace757bib33","first-page":"003","article-title":"Quantum measurements and the Abelian stabilizer problem","volume":"TR96","author":"Kitaev","year":"1996","journal-title":"Electron. Coll. Comput. Complex."},{"key":"mlstace757bib34","article-title":"QMware | the first global quantum cloud","author":"","year":"2022"},{"key":"mlstace757bib35","article-title":"PennyLane: automatic differentiation of hybrid quantum-classical computations","author":"Bergholm","year":"2018"},{"key":"mlstace757bib36","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/15\/12\/123012","article-title":"A quantum information processor with trapped ions","volume":"15","author":"Schindler","year":"2013","journal-title":"New J. Phys."},{"key":"mlstace757bib37","doi-asserted-by":"publisher","DOI":"10.1002\/qute.202300043","article-title":"Benchmarking simulated and physical quantum processing units using quantum and hybrid algorithms","volume":"6","author":"Kordzanganeh","year":"2023","journal-title":"Adv. Quantum Technol."},{"key":"mlstace757bib38","doi-asserted-by":"publisher","first-page":"5464","DOI":"10.1038\/s41467-019-13534-2","article-title":"Benchmarking an 11-qubit quantum computer","volume":"10","author":"Wright","year":"2019","journal-title":"Nat. Commun."},{"key":"mlstace757bib39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.107.012422","article-title":"Exponential data encoding for quantum supervised learning","volume":"107","author":"Shin","year":"2023","journal-title":"Phys. Rev. A"},{"key":"mlstace757bib40","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1140\/epjqt\/s40507-022-00135-0","article-title":"Fock state-enhanced expressivity of quantum machine learning models","volume":"9","author":"Yee Gan","year":"2022","journal-title":"EPJ Quantum Technol."},{"key":"mlstace757bib41","article-title":"Generalization despite overfitting in quantum machine learning models","author":"Peters","year":"2022"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace757","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace757\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace757","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace757\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace757\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace757\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace757\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace757\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,17]],"date-time":"2023-12-17T01:52:52Z","timestamp":1702777972000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace757"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,30]]},"references-count":41,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,8,30]]},"published-print":{"date-parts":[[2023,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ace757","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,30]]},"assertion":[{"value":"An exponentially-growing family of universal quantum circuits","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-02-24","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-07-13","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-08-30","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}