{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T14:25:50Z","timestamp":1766586350744,"version":"3.37.3"},"reference-count":60,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T00:00:00Z","timestamp":1706140800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T00:00:00Z","timestamp":1706140800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["No. XDB33000000"],"award-info":[{"award-number":["No. XDB33000000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 92165101"],"award-info":[{"award-number":["No. 92165101"]}],"id":[{"id":"10.13039\/501100001809","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":[[2024,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Constructing more expressive ansatz has been a primary focus for quantum Monte Carlo, aimed at more accurate <jats:italic>ab initio<\/jats:italic> calculations. However, with more powerful ansatz, e.g. various recent developed models based on neural-network architectures, the training becomes more difficult and expensive, which may have a counterproductive effect on the accuracy of calculation. In this work, we propose to make use of the training data to perform empirical variance extrapolation when using neural-network ansatz in variational Monte Carlo. We show that this approach can speed up the convergence and surpass the ansatz limitation to obtain an improved estimation of the energy. Moreover, variance extrapolation greatly enhances the error cancellation capability, resulting in significantly improved relative energy outcomes, which are the keys to chemistry and physics problems.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad1f75","type":"journal-article","created":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T22:21:54Z","timestamp":1705530114000},"page":"015016","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Variance extrapolation method for neural-network variational Monte Carlo"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5545-2221","authenticated-orcid":true,"given":"Weizhong","family":"Fu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiluo","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1603-1963","authenticated-orcid":true,"given":"Ji","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,1,25]]},"reference":[{"key":"mlstad1f75bib1","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1103\/RevModPhys.73.33","article-title":"Quantum Monte Carlo simulations of solids","volume":"73","author":"Foulkes","year":"2001","journal-title":"Rev. Mod. Phys."},{"key":"mlstad1f75bib2","doi-asserted-by":"publisher","first-page":"1267","DOI":"10.1103\/RevModPhys.71.1267","article-title":"Nobel lecture: quantum chemical models","volume":"71","author":"Pople","year":"1999","journal-title":"Rev. Mod. Phys."},{"key":"mlstad1f75bib3","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1103\/RevModPhys.71.1253","article-title":"Nobel lecture: electronic structure of matter-wave functions and density functionals","volume":"71","author":"Kohn","year":"1999","journal-title":"Rev. Mod. Phys."},{"key":"mlstad1f75bib4","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1098\/rspa.1929.0094","article-title":"Quantum mechanics of many-electron systems","volume":"123","author":"Dirac","year":"1929","journal-title":"Proc. R. Soc. A"},{"key":"mlstad1f75bib5","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1103\/RevModPhys.87.897","article-title":"Density functional theory: its origins, rise to prominence, and future","volume":"87","author":"Jones","year":"2015","journal-title":"Rev. Mod. Phys."},{"key":"mlstad1f75bib6","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1021\/cr2001564","article-title":"Quantum Monte Carlo and related approaches","volume":"112","author":"Austin","year":"2012","journal-title":"Chem. Rev."},{"key":"mlstad1f75bib7","doi-asserted-by":"publisher","first-page":"A442","DOI":"10.1103\/PhysRev.138.A442","article-title":"Ground state of liquid He 4","volume":"138","author":"McMillan","year":"1965","journal-title":"Phys. Rev."},{"key":"mlstad1f75bib8","doi-asserted-by":"publisher","first-page":"3081","DOI":"10.1103\/PhysRevB.16.3081","article-title":"Monte Carlo simulation of a many-fermion study","volume":"16","author":"Ceperley","year":"1977","journal-title":"Phys. Rev. B"},{"key":"mlstad1f75bib9","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":"mlstad1f75bib10","article-title":"Schnet: a continuous-filter convolutional neural network for modeling quantum interactions","volume":"vol 30","author":"Sch\u00fctt","year":"2017"},{"key":"mlstad1f75bib11","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1038\/s41467-017-00705-2","article-title":"Efficient representation of quantum many-body states with deep neural networks","volume":"8","author":"Gao","year":"2017","journal-title":"Nat. Commun."},{"key":"mlstad1f75bib12","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.97.035116","article-title":"Approximating quantum many-body wave functions using artificial neural networks","volume":"97","author":"Cai","year":"2018","journal-title":"Phys. Rev. B"},{"key":"mlstad1f75bib13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2019.108929","article-title":"Solving many-electron Schr\u00f6dinger equation using deep neural networks","volume":"399","author":"Han","year":"2019","journal-title":"J. Comput. Phys."},{"key":"mlstad1f75bib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.122.226401","article-title":"Backflow transformations via neural networks for quantum many-body wave functions","volume":"122","author":"Luo","year":"2019","journal-title":"Phys. Rev. Lett."},{"key":"mlstad1f75bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.033429","article-title":"Ab initio solution of the many-electron Schr\u00f6dinger equation with deep neural networks","volume":"2","author":"Pfau","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"mlstad1f75bib16","doi-asserted-by":"publisher","first-page":"2368","DOI":"10.1038\/s41467-020-15724-9","article-title":"Fermionic neural-network states for ab-initio electronic structure","volume":"11","author":"Choo","year":"2020","journal-title":"Nat. Commun."},{"year":"2020","author":"Spencer","article-title":"Better, faster fermionic neural networks","key":"mlstad1f75bib17"},{"key":"mlstad1f75bib18","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1038\/s41557-020-0544-y","article-title":"Deep-neural-network solution of the electronic Schr\u00f6dinger equation","volume":"12","author":"Hermann","year":"2020","journal-title":"Nat. Chem."},{"year":"2022","author":"von Glehn","article-title":"A self-attention ansatz for ab-initio quantum chemistry","key":"mlstad1f75bib19"},{"key":"mlstad1f75bib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.111765","article-title":"Explicitly antisymmetrized neural network layers for variational Monte Carlo simulation","volume":"474","author":"Lin","year":"2023","journal-title":"J. Comput. Phys."},{"year":"2022","author":"Abrahamsen","article-title":"Taming the sign problem of explicitly antisymmetrized neural networks via rough activation functions","key":"mlstad1f75bib21"},{"key":"mlstad1f75bib22","article-title":"Gold-standard solutions to the Schr\u00f6dinger equation using deep learning: how much physics do we need?","volume":"vol 35","author":"Gerard","year":"2022"},{"key":"mlstad1f75bib23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.4.023138","article-title":"Neural-network quantum states for periodic systems in continuous space","volume":"4","author":"Pescia","year":"2022","journal-title":"Phys. Rev. Res."},{"key":"mlstad1f75bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.107.235139","article-title":"Neural network ansatz for periodic wave functions and the homogeneous electron gas","volume":"107","author":"Wilson","year":"2023","journal-title":"Phys. Rev. B"},{"key":"mlstad1f75bib25","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1038\/s43588-022-00228-x","article-title":"Solving the electronic Schr\u00f6dinger equation for multiple nuclear geometries with weight-sharing deep neural networks","volume":"2","author":"Scherbela","year":"2022","journal-title":"Nat. Comput. Sci."},{"key":"mlstad1f75bib26","doi-asserted-by":"publisher","first-page":"7895","DOI":"10.1038\/s41467-022-35627-1","article-title":"Ab initio calculation of real solids via neural network ansatz","volume":"13","author":"Li","year":"2022","journal-title":"Nat. Commun."},{"year":"2021","author":"Gao","article-title":"Ab-initio potential energy surfaces by pairing GNNs with neural wave functions","key":"mlstad1f75bib27"},{"year":"2022","author":"Gao","article-title":"Sampling-free inference for ab-initio potential energy surface networks","key":"mlstad1f75bib28"},{"year":"2023","author":"Gao","article-title":"Generalizing neural wave functions","key":"mlstad1f75bib29"},{"year":"2023","author":"Scherbela","article-title":"Towards a foundation model for neural network wavefunctions","key":"mlstad1f75bib30"},{"key":"mlstad1f75bib31","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1038\/s42256-022-00461-z","article-title":"Autoregressive neural-network wavefunctions for ab initio quantum chemistry","volume":"4","author":"Barrett","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"mlstad1f75bib32","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acdb2f","article-title":"Scalable neural quantum states architecture for quantum chemistry","volume":"4","author":"Zhao","year":"2023","journal-title":"Mach. Learn. Sci. Technol."},{"key":"mlstad1f75bib33","doi-asserted-by":"publisher","first-page":"1860","DOI":"10.1038\/s41467-023-37609-3","article-title":"Towards the ground state of molecules via diffusion Monte Carlo on neural networks","volume":"14","author":"Ren","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstad1f75bib34","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1002\/andp.19273892002","article-title":"Zur quantentheorie der Molekeln","volume":"389","author":"Born","year":"1927","journal-title":"Ann. Phys., Lpz."},{"key":"mlstad1f75bib35","doi-asserted-by":"publisher","DOI":"10.1063\/1.5008743","article-title":"Excitation variance matching with limited configuration interaction expansions in variational Monte Carlo","volume":"147","author":"Robinson","year":"2017","journal-title":"J. Chem. Phys."},{"key":"mlstad1f75bib36","doi-asserted-by":"publisher","first-page":"1487","DOI":"10.1021\/acs.jpca.8b10671","article-title":"Excited state specific multi-Slater Jastrow wave functions","volume":"123","author":"Pineda Flores","year":"2019","journal-title":"J. Phys. Chem. A"},{"key":"mlstad1f75bib37","doi-asserted-by":"publisher","DOI":"10.1063\/5.0024572","article-title":"A hybrid approach to excited-state-specific variational Monte Carlo and doubly excited states","volume":"153","author":"Otis","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstad1f75bib38","doi-asserted-by":"publisher","DOI":"10.1063\/5.0020310","article-title":"A variational Monte Carlo approach for core excitations","volume":"153","author":"Garner","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstad1f75bib39","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1038\/s41467-022-35534-5","article-title":"Electronic excited states in deep variational Monte Carlo","volume":"14","author":"Entwistle","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstad1f75bib40","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.48.12037","article-title":"Effects of three-body and backflow correlations in the two-dimensional electron gas","volume":"48","author":"Kwon","year":"1993","journal-title":"Phys. Rev. B"},{"key":"mlstad1f75bib41","doi-asserted-by":"publisher","first-page":"6800","DOI":"10.1103\/PhysRevB.58.6800","article-title":"Effects of backflow correlation in the three-dimensional electron gas: quantum Monte Carlo study","volume":"58","author":"Kwon","year":"1998","journal-title":"Phys. Rev. B"},{"key":"mlstad1f75bib42","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.91.115106","article-title":"Iterative backflow renormalization procedure for many-body ground-state wave functions of strongly interacting normal fermi liquids","volume":"91","author":"Taddei","year":"2015","journal-title":"Phys. Rev. B"},{"key":"mlstad1f75bib43","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2122059119","article-title":"Fermionic wave functions from neural-network constrained hidden states","volume":"119","author":"Robledo Moreno","year":"2022","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstad1f75bib44","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.88.060402","article-title":"Direct evidence for a gapless Z 2 spin liquid by frustrating N\u00e9el antiferromagnetism","volume":"88","author":"Hu","year":"2013","journal-title":"Phys. Rev. B"},{"key":"mlstad1f75bib45","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.93.144411","article-title":"Spin liquid nature in the heisenberg J1\u2212J2 triangular antiferromagnet","volume":"93","author":"Iqbal","year":"2016","journal-title":"Phys. Rev. B"},{"key":"mlstad1f75bib46","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1143\/JPSJ.70.2287","article-title":"Path-integral renormalization group method for numerical study on ground states of strongly correlated electronic systems","volume":"70","author":"Kashima","year":"2001","journal-title":"J. Phys. Soc. Japan"},{"key":"mlstad1f75bib47","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/S0009-2614(97)01392-4","article-title":"Accurately solving the electronic Schr\u00f6dinger equation of atoms and molecules using explicitly correlated (r12-)MR-CI: the ground state potential energy curve of N2","volume":"283","author":"Gdanitz","year":"1998","journal-title":"Chem. Phys. Lett."},{"key":"mlstad1f75bib48","doi-asserted-by":"publisher","DOI":"10.1063\/1.2354502","article-title":"An accurate analytic potential function for ground-state N 2 from a direct-potential-fit analysis of spectroscopic data","volume":"125","author":"Le Roy","year":"2006","journal-title":"J. Chem. Phys."},{"year":"2022","author":"Botev","article-title":"KFAC-JAX","key":"mlstad1f75bib49"},{"key":"mlstad1f75bib50","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.7.031059","article-title":"Towards the solution of the many-electron problem in real materials: equation of state of the hydrogen chain with state-of-the-art many-body methods","volume":"7","author":"Motta","year":"2017","journal-title":"Phys. Rev. X"},{"key":"mlstad1f75bib51","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.64.016702","article-title":"Twist-averaged boundary conditions in continuum quantum Monte Carlo algorithms","volume":"64","author":"Lin","year":"2001","journal-title":"Phys. Rev. E"},{"key":"mlstad1f75bib52","first-page":"pp 2408","article-title":"Optimizing neural networks with kronecker-factored approximate curvature","author":"Martens","year":"2015"},{"key":"mlstad1f75bib53","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.97.076404","article-title":"Finite-size error in many-body simulations with long-range interactions","volume":"97","author":"Chiesa","year":"2006","journal-title":"Phys. Rev. Lett."},{"key":"mlstad1f75bib54","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.73.235124","article-title":"Local-orbital occupancy formulation of density functional theory: application to Si, C, and graphene","volume":"73","author":"Dappe","year":"2006","journal-title":"Phys. Rev. B"},{"key":"mlstad1f75bib55","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.74.066701","article-title":"Inhomogeneous backflow transformations in quantum Monte Carlo calculations","volume":"74","author":"R\u00edos","year":"2006","journal-title":"Phys. Rev. E"},{"key":"mlstad1f75bib56","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.3.033072","article-title":"Towards efficient and accurate ab initio solutions to periodic systems via transcorrelation and coupled cluster theory","volume":"3","author":"Liao","year":"2021","journal-title":"Phys. Rev. Res."},{"key":"mlstad1f75bib57","doi-asserted-by":"publisher","first-page":"3649","DOI":"10.1103\/PhysRevA.47.3649","article-title":"Ground-state correlation energies for atomic ions with 3 to 18 electrons","volume":"47","author":"Chakravorty","year":"1993","journal-title":"Phys. Rev. A"},{"key":"mlstad1f75bib58","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1103\/RevModPhys.83.851","article-title":"Nobel lecture: random walk to graphene","volume":"83","author":"Geim","year":"2011","journal-title":"Rev. Mod. Phys."},{"key":"mlstad1f75bib59","doi-asserted-by":"publisher","first-page":"5188","DOI":"10.1103\/PhysRevB.13.5188","article-title":"Special points for Brillouin-zone integrations","volume":"13","author":"Monkhorst","year":"1976","journal-title":"Phys. Rev. B"},{"key":"mlstad1f75bib60","doi-asserted-by":"publisher","first-page":"1748","DOI":"10.1103\/PhysRevB.16.1748","article-title":"\u2018Special points for Brillouin-zone integrations\u2019-a reply","volume":"16","author":"Pack","year":"1977","journal-title":"Phys. Rev. B"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1f75","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1f75\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1f75","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1f75\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1f75\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1f75\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1f75\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1f75\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T07:48:04Z","timestamp":1706168884000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1f75"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,25]]},"references-count":60,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1,25]]},"published-print":{"date-parts":[[2024,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad1f75","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2024,1,25]]},"assertion":[{"value":"Variance extrapolation method for neural-network variational Monte Carlo","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 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-07-27","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-01-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-01-25","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}