{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:02:35Z","timestamp":1770843755451,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T00:00:00Z","timestamp":1661385600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T00:00:00Z","timestamp":1661385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National University of Colombia"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Quantum Mach. Intell."],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>A density matrix describes the statistical state of a quantum system. It is a powerful formalism to represent both the quantum and classical uncertainty of quantum systems and to express different statistical operations such as measurement, system combination and expectations as linear algebra operations. This paper explores how density matrices can be used as a building block for machine learning models exploiting their ability to straightforwardly combine linear algebra and probability. One of the main results of the paper is to show that density matrices coupled with random Fourier features could approximate arbitrary probability distributions over <jats:inline-formula><jats:alternatives><jats:tex-math>$$\\mathbb {R}^{n}$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msup>\n                    <mml:mrow>\n                      <mml:mi>R<\/mml:mi>\n                    <\/mml:mrow>\n                    <mml:mi>n<\/mml:mi>\n                  <\/mml:msup>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>. Based on this finding the paper builds different models for density estimation, classification and regression. These models are differentiable, so it is possible to integrate them with other differentiable components, such as deep learning architectures and to learn their parameters using gradient-based optimization. In addition, the paper presents optimization-less training strategies based on estimation and model averaging. The models are evaluated in benchmark tasks and the results are reported and discussed.<\/jats:p>","DOI":"10.1007\/s42484-022-00079-9","type":"journal-article","created":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T09:03:58Z","timestamp":1661418238000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Learning with density matrices and random features"],"prefix":"10.1007","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9009-7288","authenticated-orcid":false,"given":"Fabio A.","family":"Gonz\u00e1lez","sequence":"first","affiliation":[]},{"given":"Alejandro","family":"Gallego","sequence":"additional","affiliation":[]},{"given":"Santiago","family":"Toledo-Cort\u00e9s","sequence":"additional","affiliation":[]},{"given":"Vladimir","family":"Vargas-Calder\u00f3n","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,8,25]]},"reference":[{"key":"79_CR1","unstructured":"Arora S, Du SS, Hu W et al (2019) On exact computation with an infinitely wide neural net. arXiv:190411955"},{"issue":"120","key":"79_CR2","first-page":"1","volume":"17","author":"H Avron","year":"2016","unstructured":"Avron H, Sindhwani V, Yang J et al (2016) Quasi-monte carlo feature maps for shift-invariant kernels. J Mach Learn Res 17(120):1\u201338. http:\/\/jmlr.org\/papers\/v17\/14-538.html","journal-title":"J Mach Learn Res"},{"key":"79_CR3","unstructured":"Avron H, Kapralov M, Musco C et al (2017) Random fourier features for kernel ridge regression: Approximation bounds and statistical guarantees. In: International conference on machine learning, PMLR, pp 253\u2013262"},{"key":"79_CR4","unstructured":"Balakrishnan S, Narayanan S, Rinaldo A et al (2013) Cluster trees on manifolds. arXiv:13076515"},{"key":"79_CR5","unstructured":"Bishop CM (2006) Pattern recognition and machine learning (information science and statistics)"},{"key":"79_CR6","doi-asserted-by":"crossref","unstructured":"Charikar M, Siminelakis P (2017) Hashing-based-estimators for kernel density in high dimensions. In: 2017 IEEE 58Th annual symposium on foundations of computer science (FOCS). IEEE, pp 1032\u20131043","DOI":"10.1109\/FOCS.2017.99"},{"issue":"1","key":"79_CR7","first-page":"5845","volume":"18","author":"F Chazal","year":"2017","unstructured":"Chazal F, Fasy B, Lecci F, et al. (2017) Robust topological inference: Distance to a measure and kernel distance. The Journal of Machine Learning Research 18(1):5845\u20135884","journal-title":"The Journal of Machine Learning Research"},{"issue":"1","key":"79_CR8","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1214\/15-EJS1102","volume":"10","author":"YC Chen","year":"2016","unstructured":"Chen Y C, Genovese C R, Wasserman L, et al. (2016) A comprehensive approach to mode clustering. Electronic Journal of Statistics 10(1):210\u2013241","journal-title":"Electronic Journal of Statistics"},{"key":"79_CR9","doi-asserted-by":"publisher","unstructured":"Cheng J, Wang Z, Pollastri G (2008) A neural network approach to ordinal regression. In: Proceedings of the International Joint Conference on Neural Networks. https:\/\/doi.org\/10.1109\/IJCNN.2008.4633963, arXiv:0704.1028, vol 2014, pp 1279\u20131284","DOI":"10.1109\/IJCNN.2008.4633963"},{"issue":"4","key":"79_CR10","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1214\/14-AOS1230","volume":"42","author":"V Chernozhukov","year":"2014","unstructured":"Chernozhukov V, Chetverikov D, Kato K, et al. (2014) Gaussian approximation of suprema of empirical processes. Ann Stat 42(4):1564\u20131597","journal-title":"Ann Stat"},{"key":"79_CR11","first-page":"1019","volume":"6","author":"W Chu","year":"2005","unstructured":"Chu W, Ghahramani Z (2005) Gaussian processes for ordinal regression. J Mach Learn Res 6:1019\u20131041. http:\/\/www.jmlr.org\/papers\/volume6\/chu05a\/chu05a.pdf","journal-title":"J Mach Learn Res"},{"key":"79_CR12","first-page":"6109","volume":"30","author":"T Dao","year":"2017","unstructured":"Dao T, De Sa C, R\u00e9 C (2017) Gaussian quadrature for kernel features. Advances in neural information processing systems 30:6109","journal-title":"Advances in neural information processing systems"},{"issue":"1-3","key":"79_CR13","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1016\/j.neucom.2010.08.022","volume":"74","author":"WY Deng","year":"2010","unstructured":"Deng WY, Zheng QH, Lian S et al (2010) Ordinal extreme learning machine. Neurocomputing 74(1-3):447\u2013456. https:\/\/doi.org\/10.1016\/j.neucom.2010.08.022","journal-title":"Neurocomputing"},{"key":"79_CR14","doi-asserted-by":"crossref","unstructured":"Efron B (1992) Bootstrap methods: another look at the jackknife. In: Breakthroughs in statistics. Springer, pp 569\u2013593","DOI":"10.1007\/978-1-4612-4380-9_41"},{"issue":"11","key":"79_CR15","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1109\/TNNLS.2014.2304976","volume":"25","author":"F Fernandez-Navarro","year":"2014","unstructured":"Fernandez-Navarro F, Riccardi A, Carloni S (2014) Ordinal neural networks without iterative tuning. IEEE Transactions on Neural Networks and Learning Systems 25(11):2075\u20132085. https:\/\/doi.org\/10.1109\/TNNLS.2014.2304976","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"79_CR16","unstructured":"Garg B, Manwani N (2020) Robust deep ordinal regression under label noise. In: Pan SJ, Sugiyama M (eds) Proceedings of The 12th Asian Conference on Machine Learning, Proceedings of Machine Learning Research, vol 129. PMLR, Bangkok, Thailand, pp 782\u2013796. http:\/\/proceedings.mlr.press\/v129\/garg20a.html"},{"issue":"4","key":"79_CR17","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.1214\/14-AOS1218","volume":"42","author":"CR Genovese","year":"2014","unstructured":"Genovese C R, Perone-Pacifico M, Verdinelli I et al (2014) Nonparametric ridge estimation. Ann Stat 42(4):1511\u20131545","journal-title":"Ann Stat"},{"key":"79_CR18","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez FA, Vargas-Calder\u00f3n V, Vinck-Posada H (2020) Supervised learning with quantum measurements. arXiv:2004.01227","DOI":"10.7566\/JPSJ.90.044002"},{"issue":"4","key":"79_CR19","doi-asserted-by":"publisher","first-page":"044,002","DOI":"10.7566\/JPSJ.90.044002","volume":"90","author":"FA Gonz\u00e1lez","year":"2021","unstructured":"Gonz\u00e1lez F A, Vargas-Calder\u00f3n V, Vinck-Posada H (2021) Classification with quantum measurements. J Phys Soc Jpn 90(4):044,002","journal-title":"J Phys Soc Jpn"},{"key":"79_CR20","doi-asserted-by":"crossref","unstructured":"Gray A G, Moore A W (2003) Nonparametric density estimation: Toward computational tractability. In: Proceedings of the 2003 SIAM International Conference on Data Mining, SIAM, pp 203\u2013211","DOI":"10.1137\/1.9781611972733.19"},{"issue":"1","key":"79_CR21","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/TKDE.2015.2457911","volume":"28","author":"PA Guti\u00e9rrez","year":"2016","unstructured":"Guti\u00e9rrez P A, P\u00e9rez-Ortiz M, S\u00e1nchez-Monedero J, et al. (2016) Ordinal regression methods: Survey and experimental study. IEEE Trans Knowl Data Eng 28(1):127\u2013146. https:\/\/doi.org\/10.1109\/TKDE.2015.2457911","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"79_CR22","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning: data mining, inference, and prediction","author":"T Hastie","year":"2009","unstructured":"Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction. Springer Science & Business Media, Berlin"},{"key":"79_CR23","unstructured":"Ji Z, Telgarsky M (2019) Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow relu networks. arXiv:190912292"},{"key":"79_CR24","unstructured":"Le Q, Sarlos T, Smola A (2013) Fastfood - approximating kernel expansions in loglinear time. In: 30th international conference on machine learning (ICML). http:\/\/jmlr.org\/proceedings\/papers\/v28\/le13.html"},{"issue":"4","key":"79_CR25","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun Y, Boser B, Denker J S, et al. (1989) Backpropagation applied to handwritten zip code recognition. Neural computation 1(4):541\u2013551","journal-title":"Neural computation"},{"key":"79_CR26","unstructured":"Li CL, Chang WC, Mroueh Y et al (2019) Implicit kernel learning. In: The 22nd international conference on artificial intelligence and statistics, PMLR, pp 2007\u20132016"},{"key":"79_CR27","doi-asserted-by":"publisher","unstructured":"Li Q, Stefani A, Toto G et al (2020) Towards multimodal sentiment analysis inspired by the quantum theoretical framework. In: 2020 IEEE conference on multimedia information processing and retrieval (MIPR), pp 177\u2013180. https:\/\/doi.org\/10.1109\/MIPR49039.2020.00044","DOI":"10.1109\/MIPR49039.2020.00044"},{"key":"79_CR28","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.inffus.2020.08.006","volume":"65","author":"Q Li","year":"2021","unstructured":"Li Q, Gkoumas D, Lioma C et al (2021) Quantum-inspired multimodal fusion for video sentiment analysis. Information Fusion 65:58\u201371. https:\/\/doi.org\/10.1016\/j.inffus.2020.08.006. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1566253520303365","journal-title":"Information Fusion"},{"issue":"2","key":"79_CR29","doi-asserted-by":"publisher","first-page":"A1089","DOI":"10.1137\/140989546","volume":"37","author":"WB March","year":"2015","unstructured":"March W B, Xiao B, Biros G (2015) Askit: Approximate skeletonization kernel-independent treecode in high dimensions. SIAM J Sci Comput 37(2):A1089\u2013A1110","journal-title":"SIAM J Sci Comput"},{"issue":"2","key":"79_CR30","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1177\/0272989X8400400203","volume":"4","author":"BJ McNeil","year":"1984","unstructured":"McNeil B J, Hanley J A (1984) Statistical approaches to the analysis of receiver operating characteristic (roc) curves. Med Dec Making 4(2):137\u2013150","journal-title":"Med Dec Making"},{"issue":"3","key":"79_CR31","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1137\/1109069","volume":"9","author":"EA Nadaraya","year":"1964","unstructured":"Nadaraya E A (1964) Some new estimates for distribution functions. Theory of Probability & Its Applications 9(3):497\u2013500","journal-title":"Theory of Probability & Its Applications"},{"issue":"3","key":"79_CR32","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1214\/aoms\/1177704472","volume":"33","author":"E Parzen","year":"1962","unstructured":"Parzen E (1962) On estimation of a probability density function and mode. The Annals of Mathematical Statistics 33(3):1065\u20131076","journal-title":"The Annals of Mathematical Statistics"},{"key":"79_CR33","unstructured":"Rahimi A, Recht B (2007) Random features for large-scale kernel machines. In: Proceedings of the 20th international conference on neural information processing systems. Curran Associates Inc., Red Hook, NY, USA, NIPS\u201907, p 1177\u20131184"},{"issue":"3","key":"79_CR34","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1214\/aoms\/1177728190","volume":"27","author":"M Rosenblatt","year":"1956","unstructured":"Rosenblatt M (1956) Remarks on some nonparametric estimates of a density function. Ann Math Statist 27(3):832\u2013837. https:\/\/doi.org\/10.1214\/aoms\/1177728190","journal-title":"Ann Math Statist"},{"key":"79_CR35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96424-9","volume-title":"Supervised learning with quantum computers","author":"M Schuld","year":"2018","unstructured":"Schuld M (2018) Supervised learning with quantum computers. Springer, Berlin"},{"issue":"2","key":"79_CR36","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1080\/00107514.2014.964942","volume":"56","author":"M Schuld","year":"2015","unstructured":"Schuld M, Sinayskiy I, Petruccione F (2015) An introduction to quantum machine learning. Contemp Phys 56(2):172\u2013185","journal-title":"Contemp Phys"},{"issue":"3","key":"79_CR37","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1007\/s00500-016-2478-2","volume":"22","author":"G Sergioli","year":"2018","unstructured":"Sergioli G, Santucci E, Didaci L, et al. (2018) A quantum-inspired version of the nearest mean classifier. Soft Comput 22(3):691\u2013705. https:\/\/doi.org\/10.1007\/s00500-016-2478-2","journal-title":"Soft Comput"},{"key":"79_CR38","doi-asserted-by":"crossref","unstructured":"Shen W, Yang Z, Wang J (2017) Random features for shift-invariant kernels with moment matching. In: Proceedings of the AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.10825"},{"key":"79_CR39","unstructured":"Sun Y, Gilbert A, Tewari A (2018) But how does it work in theory? linear svm with random features. arXiv:180904481"},{"key":"79_CR40","doi-asserted-by":"crossref","unstructured":"Tang E (2019a) A quantum-inspired classical algorithm for recommendation systems. In: Proceedings of the 51st annual ACM SIGACT symposium on theory of computing, pp 217\u2013228","DOI":"10.1145\/3313276.3316310"},{"key":"79_CR41","unstructured":"Tang E (2019b) Quantum-inspired classical algorithms for principal component analysis and supervised clustering. arXiv:1811.00414"},{"key":"79_CR42","doi-asserted-by":"publisher","first-page":"42,354","DOI":"10.1109\/ACCESS.2019.2904624","volume":"7","author":"P Tiwari","year":"2019","unstructured":"Tiwari P, Melucci M (2019) Towards a quantum-inspired binary classifier. IEEE Access 7:42,354\u201342,372. https:\/\/doi.org\/10.1109\/ACCESS.2019.2904624","journal-title":"IEEE Access"},{"key":"79_CR43","unstructured":"Tiwari P, Dehdashti S, Obeid AK et al (2020) Kernel method based on non-linear coherent state. arXiv:200707887"},{"key":"79_CR44","first-page":"245","volume":"1927","author":"J Von Neumann","year":"1927","unstructured":"Von Neumann J (1927) Wahrscheinlichkeitstheoretischer aufbau der quantenmechanik. Nachrichten von der Gesellschaft der Wissenschaften zu g\u00f6ttingen. Mathematisch-Physikalische Klasse 1927:245\u2013272","journal-title":"Mathematisch-Physikalische Klasse"},{"key":"79_CR45","unstructured":"Wilce A (2021) Quantum logic and probability theory. In: Zalta E N (ed) The stanford encyclopedia of philosophy, fall 2021 edn. Metaphysics Research Lab, Stanford University"},{"key":"79_CR46","unstructured":"Wolf L (2006) Learning using the born rule. Tech. rep., Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory"},{"key":"79_CR47","unstructured":"Xie B, Liang Y, Song L (2015) Scale up nonlinear component analysis with doubly stochastic gradients. arXiv:150403655"},{"key":"79_CR48","unstructured":"Yu FXX, Suresh AT, Choromanski KM et al (2016) Orthogonal random features. In: Lee D, Sugiyama M, Luxburg U et al (eds) Advances in neural information processing systems, vol 29. Curran Associates, Inc., pp 1975\u20131983. https:\/\/proceedings.neurips.cc\/paper\/2016\/file\/53adaf494dc89ef7196d73636eb2451b-Paper.pdf"},{"key":"79_CR49","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.tcs.2018.04.029","volume":"752","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Song D, Zhang P et al (2018) A quantum-inspired multimodal sentiment analysis framework. Theor Comput Sci 752:21\u201340. https:\/\/doi.org\/10.1016\/j.tcs.2018.04.029. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0304397518302639, quantum structures in computer science: language, semantics, retrieval","journal-title":"Theor Comput Sci"},{"key":"79_CR50","doi-asserted-by":"crossref","unstructured":"Zhang Y, Li Q, Song D et al (2019) Quantum-inspired interactive networks for conversational sentiment analysis. In: 28th international joint conference on artificial intelligence (IJCAI2019). http:\/\/oro.open.ac.uk\/61755\/","DOI":"10.24963\/ijcai.2019\/755"}],"updated-by":[{"DOI":"10.1007\/s42484-024-00164-1","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T00:00:00Z","timestamp":1715644800000}}],"container-title":["Quantum Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-022-00079-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42484-022-00079-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-022-00079-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T13:04:53Z","timestamp":1715691893000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42484-022-00079-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,25]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["79"],"URL":"https:\/\/doi.org\/10.1007\/s42484-022-00079-9","relation":{"correction":[{"id-type":"doi","id":"10.1007\/s42484-024-00164-1","asserted-by":"object"}]},"ISSN":["2524-4906","2524-4914"],"issn-type":[{"value":"2524-4906","type":"print"},{"value":"2524-4914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,25]]},"assertion":[{"value":"8 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2024","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s42484-024-00164-1","URL":"https:\/\/doi.org\/10.1007\/s42484-024-00164-1","order":7,"name":"change_details","label":"Change Details","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":"<!--Emphasis Type='Bold' removed-->Conflict of interest"}}],"article-number":"23"}}