{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T17:36:12Z","timestamp":1726076172044},"reference-count":35,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T00:00:00Z","timestamp":1653523200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T00:00:00Z","timestamp":1653523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Beijing Outstanding Young Scientist Program"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11734010"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,6,1]]},"abstract":"Abstract<\/jats:title>\n Analytic continuation maps imaginary-time Green\u2019s functions obtained by various theoretical\/numerical methods to real-time response functions that can be directly compared with experiments. Analytic continuation is an important bridge between many-body theories and experiments but is also a challenging problem because such mappings are ill-conditioned. In this work, we develop a neural network (NN)-based method for this problem. The training data is generated either using synthetic Gaussian-type spectral functions or from exactly solvable models where the analytic continuation can be obtained analytically. Then, we applied the trained NN to the testing data, either with synthetic noise or intrinsic noise in Monte Carlo simulations. We conclude that the best performance is always achieved when a proper amount of noise is added to the training data. Moreover, our method can successfully capture multi-peak structure in the resulting response function for the cases with the best performance. The method can be combined with Monte Carlo simulations to compare with experiments on real-time dynamics.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac6f44","type":"journal-article","created":{"date-parts":[[2022,5,12]],"date-time":"2022-05-12T22:25:16Z","timestamp":1652394316000},"page":"025010","update-policy":"http:\/\/dx.doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Noise enhanced neural networks for analytic continuation"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-7450-3987","authenticated-orcid":true,"given":"Juan","family":"Yao","sequence":"first","affiliation":[]},{"given":"Ce","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhiyuan","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Zhai","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2022,5,26]]},"reference":[{"key":"mlstac6f44bib1","author":"Gubernatis","year":"2016"},{"key":"mlstac6f44bib2","volume":"vol 2","author":"Pavarini","year":"2012"},{"key":"mlstac6f44bib3","author":"Suzuki","year":"1993"},{"key":"mlstac6f44bib4","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1103\/RevModPhys.83.349","article-title":"Continuous-time Monte Carlo methods for quantum impurity models","volume":"83","author":"Gull","year":"2011","journal-title":"Rev. Mod. Phys."},{"key":"mlstac6f44bib5","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1080\/23746149.2017.1288585","article-title":"Statistical and computational intelligence approach to analytic continuation in quantum Monte Carlo","volume":"2","author":"Bertaina","year":"2017","journal-title":"Adv. Phys. X"},{"key":"mlstac6f44bib6","author":"Mahan","year":"2000"},{"key":"mlstac6f44bib7","author":"Altland","year":"2010","edition":"2nd edn"},{"key":"mlstac6f44bib8","author":"Ramm","year":"2004"},{"key":"mlstac6f44bib9","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1515\/JIIP.2008.019","article-title":"Definitions and examples of inverse and ill-posed problems","volume":"16","author":"Kabanikhin","year":"2008","journal-title":"J. Inverse Ill-Posed Problems"},{"key":"mlstac6f44bib10","author":"Kabanikhin","year":"2011"},{"key":"mlstac6f44bib11","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/0370-1573(95)00074-7","article-title":"Bayesian inference and the analytic continuation of imaginary-time quantum Monte Carlo data","volume":"269","author":"Jarrell","year":"1996","journal-title":"Phys. Rep."},{"key":"mlstac6f44bib12","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.94.023303","article-title":"Algorithms for optimized maximum entropy and diagnostic tools for analytic continuation","volume":"94","author":"Bergeron","year":"2016","journal-title":"Phys. Rev. E"},{"key":"mlstac6f44bib13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.98.205102","article-title":"Maximum quantum entropy method","volume":"98","author":"Sim","year":"2018","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.96.155128","article-title":"Maximum entropy formalism for the analytic continuation of matrix-valued Green\u2019s functions","volume":"96","author":"Kraberger","year":"2017","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib15","doi-asserted-by":"publisher","first-page":"2380","DOI":"10.1103\/PhysRevB.41.2380","article-title":"Maximum-entropy method for analytic continuation of quantum Monte Carlo data","volume":"41","author":"Silver","year":"1990","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.81.155107","article-title":"Analytical continuation of imaginary axis data using maximum entropy","volume":"81","author":"Gunnarsson","year":"2010","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.92.060509","article-title":"Maximum entropy analytic continuation for spectral functions with nonpositive spectral weight","volume":"92","author":"Reymbaut","year":"2015","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.100.075137","article-title":"Bayesian parametric analytic continuation of Green\u2019s functions","volume":"100","author":"Rumetshofer","year":"2019","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.57.10287","article-title":"Stochastic method for analytic continuation of quantum Monte Carlo data","volume":"57","author":"Sandvik","year":"1998","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.81.056701","article-title":"Analytic continuation of quantum Monte Carlo data by stochastic analytical inference","volume":"81","author":"Fuchs","year":"2010","journal-title":"Phys. Rev. E"},{"key":"mlstac6f44bib21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.94.063308","article-title":"Constrained sampling method for analytic continuation","volume":"94","author":"Sandvik","year":"2016","journal-title":"Phys. Rev. E"},{"key":"mlstac6f44bib22","doi-asserted-by":"publisher","first-page":"6317","DOI":"10.1103\/PhysRevB.62.6317","article-title":"Diagrammatic quantum Monte Carlo study of the Fr\u00f6hlich polaron","volume":"62","author":"Mishchenko","year":"2000","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.95.014102","article-title":"Numerical analytic continuation: answers to well-posed questions","volume":"95","author":"Goulko","year":"2017","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.101.085111","article-title":"Average spectrum method for analytic continuation: efficient blocked-mode sampling and dependence on the discretization grid","volume":"101","author":"Ghanem","year":"2020","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.102.035114","article-title":"Extending the average spectrum method: grid point sampling and density averaging","volume":"102","author":"Ghanem","year":"2020","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib26","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1038\/nphys2913","article-title":"The dynamics of quantum criticality revealed by quantum Monte Carlo and holography","volume":"10","author":"Witczak-Krempa","year":"2014","journal-title":"Nat. Phys."},{"key":"mlstac6f44bib27","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aa8d93","article-title":"Projected regression method for solving Fredholm integral equations arising in the analytic continuation problem of quantum physics","volume":"33","author":"Arsenault","year":"2017","journal-title":"Inverse Problems"},{"key":"mlstac6f44bib28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.98.245101","article-title":"Analytic continuation via domain knowledge free machine learning","volume":"98","author":"Yoon","year":"2018","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib29","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.056401","article-title":"Artificial neural network approach to the analytic continuation problem","volume":"124","author":"Fournier","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstac6f44bib30","article-title":"Learned optimizers for analytic continuation","author":"Huang","year":"2021"},{"key":"mlstac6f44bib31","author":"Goodfellow","year":"2016"},{"key":"mlstac6f44bib32","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.102.094101","article-title":"Worm-algorithm-type simulation of the quantum transverse-field Ising model","volume":"102","author":"Huang","year":"2020","journal-title":"Phys. Rev. B"},{"key":"mlstac6f44bib33","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.94.051605","article-title":"Dark continuum in the spectral function of the resonant Fermi polaron","volume":"94","author":"Goulko","year":"2016","journal-title":"Phys. Rev. A"},{"key":"mlstac6f44bib34","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/S0375-9601(97)00957-2","article-title":"Worm algorithm in quantum Monte Carlo simulations","volume":"238","author":"Prokof\u2019ev","year":"1998","journal-title":"Phys. Lett. A"},{"key":"mlstac6f44bib35","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1134\/1.558661","article-title":"Exact, complete and universal continuous-time worldline Monte Carlo approach to the statistics of discrete quantum systems","volume":"87","author":"Prokof\u2019ev","year":"1998","journal-title":"J. Exp. Theor. Phys."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac6f44","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac6f44\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac6f44","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac6f44\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac6f44\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac6f44\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac6f44\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac6f44\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T12:48:29Z","timestamp":1653569309000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac6f44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,26]]},"references-count":35,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,5,26]]},"published-print":{"date-parts":[[2022,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac6f44","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,26]]},"assertion":[{"value":"Noise enhanced neural networks for analytic continuation","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 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-05-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-05-12","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-05-26","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}