{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T12:30:47Z","timestamp":1766493047694,"version":"3.48.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Aker Scholarship"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Comput Sci"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Deep-learning-based variational Monte Carlo has emerged as a highly accurate method for solving the many-electron Schr\u00f6dinger equation. Despite favorable scaling with the number of electrons,\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:tex-math>$${\\mathcal{O}}({{n}_{{\\rm{el}}}}^{4})$$<\/jats:tex-math>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <mml:mrow>\n                            <mml:mi>O<\/mml:mi>\n                            <mml:mrow>\n                              <mml:mo>(<\/mml:mo>\n                              <mml:mrow>\n                                <mml:msup>\n                                  <mml:mrow>\n                                    <mml:msub>\n                                      <mml:mrow>\n                                        <mml:mi>n<\/mml:mi>\n                                      <\/mml:mrow>\n                                      <mml:mrow>\n                                        <mml:mi>el<\/mml:mi>\n                                      <\/mml:mrow>\n                                    <\/mml:msub>\n                                  <\/mml:mrow>\n                                  <mml:mrow>\n                                    <mml:mn>4<\/mml:mn>\n                                  <\/mml:mrow>\n                                <\/mml:msup>\n                              <\/mml:mrow>\n                              <mml:mo>)<\/mml:mo>\n                            <\/mml:mrow>\n                          <\/mml:mrow>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    , the practical value of deep-learning-based variational Monte Carlo is limited by the high cost of optimizing the neural network weights for every system studied. Recent research has proposed optimizing a single neural network across multiple systems, reducing the cost per system. Here we extend this approach to solids, which require numerous calculations across different geometries, boundary conditions and supercell sizes. We demonstrate that optimization of a single ansatz across these variations significantly reduces optimization steps. Furthermore, we successfully transfer a network trained on 2\u2009\u00d7\u20092\u2009\u00d7\u20092 supercells of LiH, to 3\u2009\u00d7\u20093\u2009\u00d7\u20093 supercells, reducing the number of optimization steps required to simulate the large system by a factor of 50 compared with previous work.\n                  <\/jats:p>","DOI":"10.1038\/s43588-025-00872-z","type":"journal-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:03:26Z","timestamp":1761123806000},"page":"1147-1157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Transferable neural wavefunctions for solids"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3314-396X","authenticated-orcid":false,"given":"L.","family":"Gerard","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2751-0572","authenticated-orcid":false,"given":"M.","family":"Scherbela","sequence":"additional","affiliation":[]},{"given":"H.","family":"Sutterud","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8359-1122","authenticated-orcid":false,"given":"W. M. C.","family":"Foulkes","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9205-0969","authenticated-orcid":false,"given":"P.","family":"Grohs","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,22]]},"reference":[{"key":"872_CR1","doi-asserted-by":"publisher","first-page":"110902","DOI":"10.1063\/1.3369628","volume":"132","author":"CD Sherrill","year":"2010","unstructured":"Sherrill, C. D. Frontiers in electronic structure theory. J. Chem. Phys. 132, 110902 (2010).","journal-title":"J. Chem. Phys."},{"key":"872_CR2","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1103\/PhysRevLett.77.3865","volume":"77","author":"JP Perdew","year":"1996","unstructured":"Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865\u20133868 (1996).","journal-title":"Phys. Rev. Lett."},{"key":"872_CR3","first-page":"031058","volume":"10","author":"Simons Collaboration on the Many-Electron Problem.","year":"2020","unstructured":"Simons Collaboration on the Many-Electron Problem. Ground-state properties of the hydrogen chain: dimerization, insulator-to-metal transition, and magnetic phases. Phys. Rev. X 10, 031058 (2020).","journal-title":"Phys. Rev. X"},{"key":"872_CR4","doi-asserted-by":"publisher","first-page":"150901","DOI":"10.1063\/1.4704546","volume":"136","author":"K Burke","year":"2012","unstructured":"Burke, K. Perspective on density functional theory. J. Chem. Phys. 136, 150901 (2012).","journal-title":"J. Chem. Phys."},{"key":"872_CR5","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1103\/RevModPhys.73.33","volume":"73","author":"WMC Foulkes","year":"2001","unstructured":"Foulkes, W. M. C., Mitas, L., Needs, R. J. & Rajagopal, G. Quantum Monte Carlo simulations of solids. Rev. Mod. Phys. 73, 33\u201383 (2001).","journal-title":"Rev. Mod. Phys."},{"key":"872_CR6","doi-asserted-by":"publisher","first-page":"033429","DOI":"10.1103\/PhysRevResearch.2.033429","volume":"2","author":"D Pfau","year":"2020","unstructured":"Pfau, D., Spencer, J. S., Matthews, Alexander, G. D. G. & Foulkes, W. M. C. Ab initio solution of the many-electron Schr\u201ddinger equation with deep neural networks. Phys. Rev. Res 2, 033429 (2020).","journal-title":"Phys. Rev. Res"},{"key":"872_CR7","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1126\/science.aag2302","volume":"355","author":"G Carleo","year":"2017","unstructured":"Carleo, G. & Matthias, T. Solving the quantum many-body problem with artificial neural networks. Science 355, 602\u2013606 (2017).","journal-title":"Science"},{"key":"872_CR8","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1038\/s41557-020-0544-y","volume":"12","author":"J Hermann","year":"2020","unstructured":"Hermann, J., Sch\u00e4tzle, Z. & No\u00e9, F. Deep-neural-network solution of the electronic Schr\u00f6dinger equation. Nat. Chem. 12, 891\u2013897 (2020).","journal-title":"Nat. Chem."},{"key":"872_CR9","first-page":"10282","volume":"35","author":"L Gerard","year":"2022","unstructured":"Gerard, L. et al. Gold-standard solutions to the schr\u00f6dinger equation using deep learning: how much physics do we need?. Adv. Neural Inf. Process. Syst. 35, 10282\u201310294 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"doi-asserted-by":"publisher","unstructured":"von Glehn, I., Spencer, J. S. & Pfau, D. A self-attention ansatz for ab initio quantum chemistry. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2211.13672 (2022).","key":"872_CR10","DOI":"10.48550\/arXiv.2211.13672"},{"key":"872_CR11","doi-asserted-by":"publisher","first-page":"167204","DOI":"10.1103\/PhysRevLett.121.167204","volume":"121","author":"K Choo","year":"2018","unstructured":"Choo, K., Carleo, G., Regnault, N. & Neupert, T. Symmetries and many-body excitations with neural-network quantum states. Phys. Rev. Lett. 121, 167204 (2018).","journal-title":"Phys. Rev. Lett."},{"key":"872_CR12","doi-asserted-by":"publisher","first-page":"020503","DOI":"10.1103\/PhysRevLett.124.020503","volume":"124","author":"O Sharir","year":"2020","unstructured":"Sharir, O., Levine, Y., Wies, N., Carleo, G. & Shashua, A. Deep autoregressive models for the efficient variational simulation of many-body quantum systems. Phys. Rev. Lett. 124, 020503 (2020).","journal-title":"Phys. Rev. Lett."},{"key":"872_CR13","doi-asserted-by":"publisher","first-page":"226401","DOI":"10.1103\/PhysRevLett.122.226401","volume":"122","author":"D Luo","year":"2019","unstructured":"Luo, D. & Clark, B. K. Backflow transformations via neural networks for quantum many-body wave functions. Phys. Rev. Lett. 122, 226401 (2019).","journal-title":"Phys. Rev. Lett."},{"key":"872_CR14","doi-asserted-by":"publisher","first-page":"036401","DOI":"10.1103\/PhysRevLett.130.036401","volume":"130","author":"G Cassella","year":"2023","unstructured":"Cassella, G. et al. Discovering quantum phase transitions with fermionic neural networks. Phys. Rev. Lett. 130, 036401 (2023).","journal-title":"Phys. Rev. Lett."},{"issue":"3","key":"872_CR15","doi-asserted-by":"publisher","first-page":"035108","DOI":"10.1103\/PhysRevB.110.035108","volume":"110","author":"G Pescia","year":"2024","unstructured":"Pescia, G., Nys, J., Kim, J., Lovato, A. & Carleo, G. Message-passing neural quantum states for the homogeneous electron gas. Phys. Rev. B 110(3), 035108 (2024).","journal-title":"Phys. Rev. B"},{"key":"872_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42005-024-01613-w","volume":"7","author":"J Kim","year":"2024","unstructured":"Kim, J. et al. Neural-network quantum states for ultra-cold Fermi gases. Commun. Phys. 7, 1\u201312 (2024).","journal-title":"Commun. Phys."},{"key":"872_CR17","first-page":"021030","volume":"14","author":"WanTong Lou","year":"2024","unstructured":"Lou, WanTong et al. Neural wave functions for superfluids. Phys. Rev. X 14, 021030 (2024).","journal-title":"Phys. Rev. X"},{"key":"872_CR18","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-35627-1","volume":"13","author":"X Li","year":"2022","unstructured":"Li, X., Li, Z. & Chen, J. Ab initio calculation of real solids via neural network ansatz. Nat. Commun. 13, 7895 (2022).","journal-title":"Nat. Commun."},{"key":"872_CR19","doi-asserted-by":"publisher","first-page":"176401","DOI":"10.1103\/PhysRevLett.132.176401","volume":"132","author":"X Li","year":"2024","unstructured":"Li, X., Qian, Y. & Chen, J. Electric polarization from a many-body neural network ansatz. Phys. Rev. Lett. 132, 176401 (2024).","journal-title":"Phys. Rev. Lett."},{"key":"872_CR20","doi-asserted-by":"publisher","first-page":"016702","DOI":"10.1103\/PhysRevE.64.016702","volume":"64","author":"C Lin","year":"2001","unstructured":"Lin, C., Zong, F.-H. & Ceperley, D. M. Twist-averaged boundary conditions in continuum quantum Monte Carlo. Phys. Rev. E 64, 016702 (2001).","journal-title":"Phys. Rev. E"},{"key":"872_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-44216-9","volume":"15","author":"M Scherbela","year":"2024","unstructured":"Scherbela, M., Gerard, L. & Grohs, P. Towards a transferable fermionic neural wavefunction for molecules. Nat. Commun. 15, 120 (2024).","journal-title":"Nat. Commun."},{"key":"872_CR22","first-page":"031059","volume":"7","author":"Simons Collaboration on the Many-Electron Problem.","year":"2017","unstructured":"Simons Collaboration on the Many-Electron Problem. 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. Phys. Rev. X 7, 031059 (2017).","journal-title":"Phys. Rev. X"},{"key":"872_CR23","doi-asserted-by":"publisher","first-page":"5188","DOI":"10.1103\/PhysRevB.13.5188","volume":"13","author":"HJ Monkhorst","year":"1976","unstructured":"Monkhorst, H. J. & Pack, J. D. Special points for Brillouin-zone integrations. Phys. Rev. B 13, 5188\u20135192 (1976).","journal-title":"Phys. Rev. B"},{"key":"872_CR24","doi-asserted-by":"publisher","first-page":"024107","DOI":"10.1063\/5.0031024","volume":"154","author":"H Shi","year":"2021","unstructured":"Shi, H. & Zhang, S. Some recent developments in auxiliary-field quantum Monte Carlo for real materials. J. Chem. Phys. 154, 024107 (2021).","journal-title":"J. Chem. Phys."},{"key":"872_CR25","doi-asserted-by":"publisher","first-page":"076404","DOI":"10.1103\/PhysRevLett.97.076404","volume":"97","author":"S Chiesa","year":"2006","unstructured":"Chiesa, S., Ceperley, D. M., Martin, R. M. & Holzmann, M. Finite-size error in many-body simulations with long-range interactions. Phys. Rev. Lett. 97, 076404 (2006).","journal-title":"Phys. Rev. Lett."},{"key":"872_CR26","doi-asserted-by":"publisher","first-page":"165109","DOI":"10.1103\/PhysRevB.80.165109","volume":"80","author":"SJ Nolan","year":"2009","unstructured":"Nolan, S. J., Gillan, M. J., Alf\u00e9, D., Allan, N. L. & Manby, F. R. Calculation of properties of crystalline lithium hydride using correlated wave function theory. Phys. Rev. B 80, 165109 (2009).","journal-title":"Phys. Rev. B"},{"key":"872_CR27","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1038\/s42256-024-00794-x","volume":"6","author":"R Li","year":"2024","unstructured":"Li, R. et al. A computational framework for neural network-based variational Monte Carlo with forward Laplacian. Nat. Mach. Intell. 6, 209\u2013219 (2024).","journal-title":"Nat. Mach. Intell."},{"key":"872_CR28","doi-asserted-by":"publisher","first-page":"013021","DOI":"10.1103\/PhysRevResearch.4.013021","volume":"4","author":"X Li","year":"2022","unstructured":"Li, X., Fan, C., Ren, W. & Chen, J. Fermionic neural network with effective core potential. Phys. Rev. Res. 4, 013021 (2022).","journal-title":"Phys. Rev. Res."},{"key":"872_CR29","doi-asserted-by":"publisher","first-page":"245142","DOI":"10.1103\/PhysRevB.100.245142","volume":"100","author":"S Azadi","year":"2019","unstructured":"Azadi, S. & Foulkes, W. M. C. Efficient method for grand-canonical twist averaging in quantum Monte Carlo calculations. Phys. Rev. B 100, 245142 (2019).","journal-title":"Phys. Rev. B"},{"unstructured":"Scherbela, M., Gerard, L. & Grohs, P. Variational Monte Carlo on a budget\u2014fine-tuning pre-trained neural wavefunctions. In 37th Conference Neural Information Processing Systems (eds Oh, A. et al) 23902\u201323920 (Curran Associates, 2023).","key":"872_CR30"},{"key":"872_CR31","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1002\/andp.19213690304","volume":"369","author":"PP Ewald","year":"1921","unstructured":"Ewald, P. P. Die Berechnung Optischer und Elektrostatischer Gitterpotentiale. Ann. Phys. 369, 253\u2013287 (1921).","journal-title":"Ann. Phys."},{"unstructured":"Gao, N. & G\u00fcnnemann, S. Generalizing neural wave functions. In Proc. 40th International Conference on Machine Learning vol. 202, 10708\u201310726 (PMLR, 2023).","key":"872_CR32"},{"key":"872_CR33","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1063\/1.456153","volume":"90","author":"TH Dunning Jr","year":"1989","unstructured":"Dunning Jr, T. H. Gaussian basis sets for use in correlated molecular calculations. I. The atoms boron through neon and hydrogen. J. Chem. Phys. 90, 1007\u20131023 (1989).","journal-title":"J. Chem. Phys."},{"key":"872_CR34","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1063\/1.1699114","volume":"21","author":"N Metropolis","year":"1953","unstructured":"Metropolis, N., Rosenbluth, A. W., Rosenbluth, M. N., Teller, A. H. & Teller, E. Equation of state calculations by fast computing machines. J. Chem. Phys. 21, 1087\u20131092 (1953).","journal-title":"J. Chem. Phys."},{"key":"872_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1239\/jap\/1363784420","volume":"50","author":"C Sherlock","year":"2013","unstructured":"Sherlock, C. Optimal scaling of the random walk Metropolis: general criteria for the 0.234 acceptance rule. J. Appl. Prob. 50, 1\u201315 (2013).","journal-title":"J. Appl. Prob."},{"unstructured":"Martens, J. & Grosse, R. Optimizing neural networks with Kronecker-factored approximate curvature. In Proc. 32nd International Conference on Machine Learning 2408\u20132417 (PMLR, 2015).","key":"872_CR36"},{"key":"872_CR37","doi-asserted-by":"publisher","first-page":"9703","DOI":"10.1103\/PhysRevB.59.9703","volume":"59","author":"PL Silvestrelli","year":"1999","unstructured":"Silvestrelli, P. L. Maximally localized Wannier functions for simulations with supercells of general symmetry. Phys. Rev. B 59, 9703\u20139706 (1999).","journal-title":"Phys. Rev. B"},{"unstructured":"Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint at https:\/\/arxiv.org\/abs\/1412.6980 (2017).","key":"872_CR38"},{"key":"872_CR39","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/j.carbon.2018.08.045","volume":"140","author":"WA Diery","year":"2018","unstructured":"Diery, W. A., Moujaes, E. A. & Nunes, R. W. Nature of localized phonon modes of tilt grain boundaries in graphene. Carbon 140, 250\u2013258 (2018).","journal-title":"Carbon"},{"doi-asserted-by":"publisher","unstructured":"Scherbela, M., Grohs, P. & Gerard, L. DeepErwin for solids. Zenodo https:\/\/doi.org\/10.5281\/zenodo.16084892 (2025).","key":"872_CR40","DOI":"10.5281\/zenodo.16084892"}],"container-title":["Nature Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00872-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00872-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00872-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T10:48:59Z","timestamp":1766486939000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00872-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":40,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["872"],"URL":"https:\/\/doi.org\/10.1038\/s43588-025-00872-z","relation":{},"ISSN":["2662-8457"],"issn-type":[{"type":"electronic","value":"2662-8457"}],"subject":[],"published":{"date-parts":[[2025,10,22]]},"assertion":[{"value":"4 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}