{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:36:48Z","timestamp":1772120208283,"version":"3.50.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T00:00:00Z","timestamp":1743724800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T00:00:00Z","timestamp":1743724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Swiss Federal Institute of Technology Zurich"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Quantum Mach. Intell."],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Quantum machine learning (QML) is a rapidly expanding field that merges the principles of quantum computing with the techniques of machine learning. One of the powerful mathematical frameworks in this domain is tensor networks. These networks are used to approximate high-order tensors by contracting tensors with lower ranks. Initially developed for simulating quantum systems, tensor networks have become integral to quantum computing and, by extension, to QML. Drawing inspiration from these quantum methods, specifically the Matrix Product States (MPS), we apply them in a classical machine learning setting. Their ability to efficiently represent and manipulate complex, high-dimensional data makes them effective in a supervised learning framework. Here, we present an MPS model, in which the MPS functions as both a classifier and a generator. The dual functionality of this novel MPS model permits a strategy that enhances the traditional training of supervised MPS models. This framework is inspired by generative adversarial networks and is geared towards generating more realistic samples by reducing outliers. In addition, our contributions offer insights into the mechanics of tensor network methods for generation tasks. Specifically, we discuss alternative embedding functions and a new sampling method from non-normalized MPSs.<\/jats:p>","DOI":"10.1007\/s42484-025-00272-6","type":"journal-article","created":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T13:45:07Z","timestamp":1743860707000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A matrix product state model for simultaneous classification and generation"],"prefix":"10.1007","volume":"7","author":[{"given":"Alex","family":"Mossi","sequence":"first","affiliation":[]},{"given":"Bojan","family":"\u017dunkovi\u010d","sequence":"additional","affiliation":[]},{"given":"Kyriakos","family":"Flouris","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,4]]},"reference":[{"issue":"15","key":"272_CR1","doi-asserted-by":"publisher","first-page":"4019","DOI":"10.1109\/TSP.2017.2703882","volume":"65","author":"JA Bengua","year":"2017","unstructured":"Bengua JA et al (2017) Matrix product state for higher-order tensor compression and classification. IEEE Trans Signal Process 65(15):4019\u20134030","journal-title":"IEEE Trans Signal Process"},{"key":"272_CR2","unstructured":"Biamonte J, Bergholm V (2017) Tensor networks in a nutshell. arXiv:1708.00006"},{"key":"272_CR3","volume-title":"Pattern recognition and machine learning (information science and statistics)","author":"CM Bishop","year":"2006","unstructured":"Bishop CM (2006) Pattern recognition and machine learning (information science and statistics). Springer-Verlag, Berlin, Heidelberg"},{"issue":"1","key":"272_CR4","first-page":"8396","volume":"22","author":"R Bonnevie","year":"2021","unstructured":"Bonnevie R, Schmidt MN (2021) Matrix product states for inference in discrete probabilistic models. J Mach Learn Res 22(1):8396\u20138443","journal-title":"J Mach Learn Res"},{"issue":"22","key":"272_CR5","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8121\/aa6dc3","volume":"50","author":"JC Bridgeman","year":"2017","unstructured":"Bridgeman JC, Chubb CT (2017) Hand-waving and interpretive dance: an introductory course on tensor networks. J Phys A: Math Theor 50(22):223001","journal-title":"J Phys A: Math Theor"},{"key":"272_CR6","unstructured":"Bruognolo B, et\u00a0al (2017) Matrix product state techniques for two-dimensional systems at finite temperature. arXiv:1705.05578"},{"key":"272_CR7","doi-asserted-by":"crossref","unstructured":"Chan GK, et\u00a0al (2016) Matrix product operators, matrix product states, and ab initio density matrix renormalization group algorithms. J Chem Phys 145(1)","DOI":"10.1063\/1.4955108"},{"issue":"15","key":"272_CR8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.99.155131","volume":"99","author":"S Cheng","year":"2019","unstructured":"Cheng S et al (2019) Tree tensor networks for generative modeling. Phys Rev B 99(15):155131","journal-title":"Phys Rev B"},{"issue":"12","key":"272_CR9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.103.125117","volume":"103","author":"S Cheng","year":"2021","unstructured":"Cheng S, Wang L, Zhang P (2021) Supervised learning with projected entangled pair states. Phys Rev B 103(12):125117","journal-title":"Phys Rev B"},{"key":"272_CR10","doi-asserted-by":"publisher","first-page":"187","DOI":"10.22331\/q-2019-09-23-187","volume":"3","author":"AM Dalzell","year":"2019","unstructured":"Dalzell AM, Brand\u00e3o FG (2019) Locally accurate MPS approximations for ground states of one-dimensional gapped local Hamiltonians. Quantum 3:187","journal-title":"Quantum"},{"issue":"3","key":"272_CR11","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1137\/06066518X","volume":"30","author":"V De Silva","year":"2008","unstructured":"De Silva V, Lim L-H (2008) Tensor rank and the ill-posedness of the best low-rank approximation problem. SIAM J Matrix Anal Appl 30(3):1084\u20131127","journal-title":"SIAM J Matrix Anal Appl"},{"issue":"1","key":"272_CR12","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1088\/1361-6544\/ac337f","volume":"35","author":"E Weinan","year":"2021","unstructured":"Weinan E, Han J, Jentzen A (2021) Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning. Nonlinearity 35(1):278\u2013310. https:\/\/doi.org\/10.1088\/1361-6544\/ac337f","journal-title":"Nonlinearity"},{"key":"272_CR13","unstructured":"Efthymiou S, Hidary J, Leichenauer S (2019) Tensornetwork for machine learning. arXiv:1906.06329"},{"key":"272_CR14","unstructured":"Ferris AJ (2015) Unbiased Monte Carlo for the age of tensor networks. arXiv:1507.00767"},{"issue":"16","key":"272_CR15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.85.165146","volume":"85","author":"AJ Ferris","year":"2012","unstructured":"Ferris AJ, Vidal G (2012) Perfect sampling with unitary tensor networks. Phys Rev B 85(16):165146","journal-title":"Phys Rev B"},{"key":"272_CR16","unstructured":"Flouris K, Konukoglu E (2023) Canonical normalizing flows for manifold learning.\u00a0Oh A,\u00a0Naumann T,\u00a0Globerson A,\u00a0Saenko K,\u00a0Hardt M, and\u00a0Levine (Eds.) S, Advances in neural information processing systems (Vol.\u00a036, pp 27294\u201327314). Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paperspsfiles\/paper\/2023\/file\/572a6f16ec44f794fb3e0f8a310acbc6-Paper-Conference.pdf"},{"key":"272_CR17","unstructured":"Francuz A, Schuch N, Vanhecke B (2023) Stable and efficient differentiation of tensor network algorithms"},{"key":"272_CR18","unstructured":"Glasser I, et\u00a0al (2019) Expressive power of tensor-network factorizations for probabilistic modeling"},{"issue":"16","key":"272_CR19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.94.165116","volume":"94","author":"J Haegeman","year":"2016","unstructured":"Haegeman J, Lubich C, Oseledets I, Vandereycken B, Verstraete F (2016) Unifying time evolution and optimization with matrix product states. Phys Rev B 94(16):165116","journal-title":"Phys Rev B"},{"issue":"3","key":"272_CR20","volume":"8","author":"Z-Y Han","year":"2018","unstructured":"Han Z-Y et al (2018) Unsupervised generative modeling using matrix product states. Phys Rev X 8(3):031012","journal-title":"Phys Rev X"},{"key":"272_CR21","doi-asserted-by":"crossref","unstructured":"Hastings MB (2007) An area law for one-dimensional quantum systems. J Stat Mech: Theor Exper P08024","DOI":"10.1088\/1742-5468\/2007\/08\/P08024"},{"issue":"1","key":"272_CR22","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s42484-024-00163-2","volume":"6","author":"M Hdaib","year":"2024","unstructured":"Hdaib M, Rajasegarar S, Pan L (2024) Quantum deep learning-based anomaly detection for enhanced network security. Quant Mach Intell 6(1):26. https:\/\/doi.org\/10.1007\/s42484-024-00163-2","journal-title":"Quant Mach Intell"},{"key":"272_CR23","doi-asserted-by":"crossref","unstructured":"Hrinchuk O, Khrulkov V, Mirvakhabova L, Orlova E, Oseledets I (2019) Tensorized embedding layers for efficient model compression. arXiv:1901.10787","DOI":"10.18653\/v1\/2020.findings-emnlp.436"},{"key":"272_CR24","doi-asserted-by":"crossref","unstructured":"H\u00e5stad J (1989) Tensor rank is NP-complete","DOI":"10.1007\/BFb0035776"},{"key":"272_CR25","unstructured":"LeCun Y, Cortes C, Burges C (2010) MNIST handwritten digit database. ATT Labs 2. http:\/\/yann.lecun.com\/exdb\/mnist. Accessed 2 Apr 2025"},{"key":"272_CR26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.9.031041","volume":"9","author":"H-J Liao","year":"2019","unstructured":"Liao H-J, Liu J-G, Wang L, Xiang T (2019) Differentiable programming tensor networks. Phys Rev X 9:031041. https:\/\/doi.org\/10.1103\/PhysRevX.9.031041","journal-title":"Phys Rev X"},{"issue":"1","key":"272_CR27","doi-asserted-by":"publisher","first-page":"L012103","DOI":"10.1103\/PhysRevE.107.L012103","volume":"107","author":"J Liu","year":"2023","unstructured":"Liu J et al (2023) Tensor networks for unsupervised machine learning. Phys Rev E 107(1):L012103","journal-title":"Phys Rev E"},{"key":"272_CR28","unstructured":"Mueller Group (2020) Matrix Product States: Canonical Forms. https:\/\/muellergroup.lassp.cornell.edu\/bt2020chap4.pdf Accessed 2 Apr 2025"},{"key":"272_CR29","unstructured":"Miles E, Schwab (2016) Supervised learning with quantum-inspired tensor networks. 4799"},{"key":"272_CR30","doi-asserted-by":"publisher","first-page":"50","DOI":"10.22331\/q-2018-01-31-50","volume":"2","author":"M Navascues","year":"2018","unstructured":"Navascues M, Vertesi T (2018) Bond dimension witnesses and the structure of homogeneous matrix product states. Quantum 2:50","journal-title":"Quantum"},{"key":"272_CR31","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.aop.2014.06.013","volume":"349","author":"R Or\u00fas","year":"2014","unstructured":"Or\u00fas R (2014) A practical introduction to tensor networks: Matrix Product States and projected entangled pair states. Ann Phys 349:117","journal-title":"Ann Phys"},{"key":"272_CR32","doi-asserted-by":"crossref","unstructured":"Or\u00fas R (2019) Tensor networks for complex quantum systems. Nat Rev Phys 1(9):538\u2013550","DOI":"10.1038\/s42254-019-0086-7"},{"issue":"5","key":"272_CR33","first-page":"2295","volume":"33","author":"IV Oseledets","year":"2011","unstructured":"Oseledets IV (2011) Tensor-train decomposition. SIAM. J Sci Comput 33(5):2295\u20132317","journal-title":"J Sci Comput"},{"key":"272_CR34","unstructured":"Paszke A, et\u00a0al (2017) Automatic differentiation in Pytorch"},{"key":"272_CR35","doi-asserted-by":"crossref","unstructured":"Penrose R (1971) Applications of negative dimensional tensors. pp 221\u2013244","DOI":"10.2307\/2552599"},{"key":"272_CR36","unstructured":"Perez-Garcia D, et\u00a0al (2006) Matrix product state representations. arXiv:quant-ph\/0608197"},{"key":"272_CR37","doi-asserted-by":"crossref","unstructured":"Pozas-Kerstjens A (2023) Privacy-preserving machine learning with tensor networks. Bullet Am Phys Soc","DOI":"10.22331\/q-2024-07-25-1425"},{"key":"272_CR38","doi-asserted-by":"crossref","unstructured":"Pozas-Kerstjens A, Hern\u00e1ndez-Santana S, Monturiol JRP, L\u00f3pez MC, Scarpa G, Gonz\u00e1lez-Guill\u00e9n CE, P\u00e9rez-Garc\u00eda D (2023) Privacy-preserving machine learning with tensor networks","DOI":"10.22331\/q-2024-07-25-1425"},{"issue":"2","key":"272_CR39","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s41683-023-00115-1","volume":"12","author":"RK Ramakrishnan","year":"2023","unstructured":"Ramakrishnan RK, Ravichandran AB, Mishra A, Kaushalram A, Hegde G, Talabattula S, Rohde PP (2023) Integrated photonic platforms for quantum technology: a review. ISSS J Micro Smart Syst 12(2):83\u2013104. https:\/\/doi.org\/10.1007\/s41683-023-00115-1","journal-title":"ISSS J Micro Smart Syst"},{"issue":"1","key":"272_CR40","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.aop.2010.09.012","volume":"326","author":"U Schollw\u00f6ck","year":"2011","unstructured":"Schollw\u00f6ck U (2011) The density-matrix renormalization group in the age of matrix product states. Ann Phys 326(1):96\u2013192","journal-title":"Ann Phys"},{"issue":"1","key":"272_CR41","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s42484-024-00165-0","volume":"6","author":"T Suzuki","year":"2024","unstructured":"Suzuki T, Hasebe T, Miyazaki T (2024) Quantum support vector machines for classification and regression on a trapped-ion quantum computer. Quant Mach Intell 6(1):31. https:\/\/doi.org\/10.1007\/s42484-024-00165-0","journal-title":"Quant Mach Intell"},{"key":"272_CR42","first-page":"7537","volume":"33","author":"M Tancik","year":"2020","unstructured":"Tancik M, Srinivasan PP, Mildenhall B, Fridovich-Keil S, Raghavan N, Singhal U, Ng R (2020) Fourier features let networks learn high frequency functions in low dimensional domains. Adv Neural Inf Process Syst 33:7537\u20137547","journal-title":"Adv Neural Inf Process Syst"},{"key":"272_CR43","unstructured":"Trefethen LN (2013) Approximation theory and approximation practice. SIAM"},{"key":"272_CR44","doi-asserted-by":"crossref","unstructured":"\u017dunkovi\u010d B (2023) Positive unlabeled learning with tensor networks. Neurocomputing 126556","DOI":"10.1016\/j.neucom.2023.126556"},{"issue":"9","key":"272_CR45","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.73.094423","volume":"73","author":"F Verstraete","year":"2006","unstructured":"Verstraete F, Cirac JI (2006) Matrix product states represent ground states faithfully. Phys Rev B 73(9):094423","journal-title":"Phys Rev B"},{"issue":"22","key":"272_CR46","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.99.220405","volume":"99","author":"G Vidal","year":"2007","unstructured":"Vidal G (2007) Entanglement renormalization. Phys Rev Lett 99(22):220405","journal-title":"Phys Rev Lett"},{"key":"272_CR47","doi-asserted-by":"crossref","unstructured":"Vieijra T, Vanderstraeten L, Verstraete F (2022) Generative modeling with projected entangled-pair states. arXiv:2202.08177","DOI":"10.1103\/PhysRevB.104.235141"},{"issue":"19","key":"272_CR48","doi-asserted-by":"publisher","first-page":"2863","DOI":"10.1103\/PhysRevLett.69.2863","volume":"69","author":"SR White","year":"1992","unstructured":"White SR (1992) Density matrix formulation for quantum renormalization groups. Phys Rev Lett 69(19):2863","journal-title":"Phys Rev Lett"},{"issue":"14","key":"272_CR49","doi-asserted-by":"publisher","first-page":"10345","DOI":"10.1103\/PhysRevB.48.10345","volume":"48","author":"SR White","year":"1993","unstructured":"White SR (1993) Density-matrix algorithms for quantum renormalization groups. Phys Rev B 48(14):10345","journal-title":"Phys Rev B"},{"key":"272_CR50","unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747"},{"key":"272_CR51","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.037201","volume":"124","author":"MP Zaletel","year":"2020","unstructured":"Zaletel MP, Pollmann F (2020) Isometric tensor network states in two dimensions. Phys Rev Lett 124:037201. https:\/\/doi.org\/10.1103\/PhysRevLett.124.037201","journal-title":"Phys Rev Lett"},{"issue":"199","key":"272_CR52","first-page":"1","volume":"25","author":"B \u017dunkovi\u010d","year":"2024","unstructured":"\u017dunkovi\u010d B, Ilievski E (2024) Grokking phase transitions in learning local rules with gradient descent. J Mach Learn Res 25(199):1\u201352","journal-title":"J Mach Learn Res"}],"container-title":["Quantum Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-025-00272-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42484-025-00272-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-025-00272-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T10:40:47Z","timestamp":1750934447000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42484-025-00272-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,4]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["272"],"URL":"https:\/\/doi.org\/10.1007\/s42484-025-00272-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4632370\/v1","asserted-by":"object"}]},"ISSN":["2524-4906","2524-4914"],"issn-type":[{"value":"2524-4906","type":"print"},{"value":"2524-4914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,4]]},"assertion":[{"value":"24 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"48"}}