{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T02:16:19Z","timestamp":1777342579012,"version":"3.51.4"},"reference-count":30,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2021,11,23]],"date-time":"2021-11-23T00:00:00Z","timestamp":1637625600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,11,23]],"date-time":"2021-11-23T00:00:00Z","timestamp":1637625600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006151","name":"DOE Office of Basic Energy Sciences","doi-asserted-by":"crossref","award":["DE-SC0018946"],"award-info":[{"award-number":["DE-SC0018946"]}],"id":[{"id":"10.13039\/100006151","id-type":"DOI","asserted-by":"crossref"}]},{"name":"NSF MRSEC","award":["DMR-1719875"],"award-info":[{"award-number":["DMR-1719875"]}]},{"name":"SHAR-CNET"},{"name":"Google Quantum Research Award"},{"name":"NSF HDR-DIRSE","award":["OAC-1934714"],"award-info":[{"award-number":["OAC-1934714"]}]},{"DOI":"10.13039\/100013020","name":"Compute Canada","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100013020","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000038","name":"NSERC","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007631","name":"Canadian Institute for Advanced Research","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007631","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>With rapid progress across platforms for quantum systems, the problem of many-body quantum state reconstruction for noisy quantum states becomes an important challenge. There has been a growing interest in approaching the problem of quantum state reconstruction using generative neural network models. Here we propose the \u2018attention-based quantum tomography\u2019 (AQT), a quantum state reconstruction using an attention mechanism-based generative network that learns the mixed state density matrix of a noisy quantum state. AQT is based on the model proposed in \u2018Attention is all you need\u2019 by Vaswani <jats:italic>et al<\/jats:italic> (2017 <jats:italic>NIPS<\/jats:italic>) that is designed to learn long-range correlations in natural language sentences and thereby outperform previous natural language processing (NLP) models. We demonstrate not only that AQT outperforms earlier neural-network-based quantum state reconstruction on identical tasks but that AQT can accurately reconstruct the density matrix associated with a noisy quantum state experimentally realized in an IBMQ quantum computer. We speculate the success of the AQT stems from its ability to model quantum entanglement across the entire quantum system much as the attention model for NLP captures the correlations among words in a sentence.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac362b","type":"journal-article","created":{"date-parts":[[2021,11,3]],"date-time":"2021-11-03T22:25:30Z","timestamp":1635978330000},"page":"01LT01","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":54,"title":["Attention-based quantum tomography"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5653-4920","authenticated-orcid":false,"given":"Peter","family":"Cha","sequence":"first","affiliation":[]},{"given":"Paul","family":"Ginsparg","sequence":"additional","affiliation":[]},{"given":"Felix","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Juan","family":"Carrasquilla","sequence":"additional","affiliation":[]},{"given":"Peter L","family":"McMahon","sequence":"additional","affiliation":[]},{"given":"Eun-Ah","family":"Kim","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2021,11,23]]},"reference":[{"key":"mlstac362bbib1","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1038\/s41586-019-1666-5","article-title":"Quantum supremacy using a programmable superconducting processor","volume":"574","author":"Arute","year":"2019","journal-title":"Nature"},{"key":"mlstac362bbib2","volume":"vol 649","author":"Paris","year":"2004"},{"key":"mlstac362bbib3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.64.052312","article-title":"Measurement of qubits","volume":"64","author":"James","year":"2001","journal-title":"Phys. Rev. A"},{"key":"mlstac362bbib4","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.93.012301","article-title":"Characterizing errors on qubit operations via iterative randomized benchmarking","volume":"93","author":"Sheldon","year":"2016","journal-title":"Phys. Rev. A"},{"key":"mlstac362bbib5","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1038\/s41567-020-0932-7","article-title":"Predicting many properties of a quantum system from very few measurements","volume":"16","author":"Huang","year":"2020","journal-title":"Nat. Phys."},{"key":"mlstac362bbib6","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1038\/s41567-018-0048-5","article-title":"Neural-network quantum state tomography","volume":"14","author":"Torlai","year":"2018","journal-title":"Nat. Phys."},{"key":"mlstac362bbib7","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1038\/s42256-019-0028-1","article-title":"Reconstructing quantum states with generative models","volume":"1","author":"Carrasquilla","year":"2019","journal-title":"Nat. Mach. Intell."},{"key":"mlstac362bbib8","article-title":"Probabilistic simulation of quantum circuits with the transformer","author":"Carrasquilla","year":"2019"},{"key":"mlstac362bbib9","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1126\/science.aag2302","article-title":"Solving the quantum many-body problem with artificial neural networks","volume":"355","author":"Carleo","year":"2017","journal-title":"Science"},{"key":"mlstac362bbib10","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1038\/nature24622","article-title":"Probing many-body dynamics on a 51-atom quantum simulator","volume":"551","author":"Bernien","year":"2017","journal-title":"Nature"},{"key":"mlstac362bbib11","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.123.230504","article-title":"Integrating neural networks with a quantum simulator for state reconstruction","volume":"123","author":"Torlai","year":"2019","journal-title":"Phys. Rev. Lett."},{"key":"mlstac362bbib12","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevB.102.035108","article-title":"Reconstructing quantum molecular rotor ground states","author":"De Vlugt","year":"2020"},{"key":"mlstac362bbib13","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1364\/OPTICA.389482","article-title":"Experimental quantum homodyne tomography via machine learning","volume":"7","author":"Tiunov","year":"2020","journal-title":"Optica"},{"key":"mlstac362bbib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.240503","article-title":"Latent space purification via neural density operators","volume":"120","author":"Torlai","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstac362bbib15","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"mlstac362bbib16","article-title":"The implementation of AQT as well as all data used for this work are available at the public repository"},{"key":"mlstac362bbib17","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1179","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"mlstac362bbib18","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D16-1053","article-title":"Long short-term memory-networks for machine reading","author":"Cheng","year":"2016"},{"key":"mlstac362bbib19","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D16-1244","article-title":"A decomposable attention model for natural language inference","author":"Parikh","year":"2016"},{"key":"mlstac362bbib20","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"mlstac362bbib21","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"mlstac362bbib22","article-title":"Google\u2019s neural machine translation system: bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"mlstac362bbib23","article-title":"Outrageously large neural networks: the sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017"},{"key":"mlstac362bbib24","author":"Shen","year":"2019"},{"key":"mlstac362bbib25","article-title":"Recent work [5] showed it is possible to estimate quantum fidelity without density matrix reconstruction in the special case when the target state is a pure state"},{"key":"mlstac362bbib26","article-title":"We note that the linear growth of sample complexity in system size for the classical fidelity threshold task seen in figure 2(a) does not translate to a linear growth in system size for a quantum fidelity threshold task"},{"key":"mlstac362bbib27","article-title":"The quantum fidelity between the AQT and MLE reconstructions is 1.043"},{"key":"mlstac362bbib28","article-title":"Error regions in quantum state tomography: computational complexity caused by geometry of quantum states","author":"Suess","year":"2016"},{"key":"mlstac362bbib29","article-title":"Robust, self-consistent, closed-form tomography of quantum logic gates on a trapped ion qubit","author":"Blume-Kohout","year":"2013"},{"key":"mlstac362bbib30","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms14485","article-title":"Demonstration of qubit operations below a rigorous fault tolerance threshold with gate set tomography","volume":"8","author":"Blume-Kohout","year":"2017","journal-title":"Nat. Commun."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac362b","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac362b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac362b","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac362b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac362b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac362b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac362b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac362b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,23]],"date-time":"2021-11-23T18:13:10Z","timestamp":1637691190000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac362b"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,23]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,11,23]]},"published-print":{"date-parts":[[2022,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac362b","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,23]]},"assertion":[{"value":"Attention-based quantum tomography","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 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2021-04-02","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-11-03","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-11-23","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}