{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T01:40:25Z","timestamp":1791855625118,"version":"4.3.4"},"reference-count":84,"publisher":"AIP Publishing","issue":"24","content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,12,28]]},"abstract":"<jats:p>Neural network (NN) potentials are a natural choice for coarse-grained (CG) models. Their many-body capacity allows highly accurate approximations of the potential of mean force, promising CG simulations of unprecedented accuracy. CG NN potentials trained bottom-up via force matching (FM), however, suffer from finite data effects: They rely on prior potentials for physically sound predictions outside the training data domain, and the corresponding free energy surface is sensitive to errors in the transition regions. The standard alternative to FM for classical potentials is relative entropy (RE) minimization, which has not yet been applied to NN potentials. In this work, we demonstrate, for benchmark problems of liquid water and alanine dipeptide, that RE training is more data efficient, due to accessing the CG distribution during training, resulting in improved free energy surfaces and reduced sensitivity to prior potentials. In addition, RE learns to correct time integration errors, allowing larger time steps in CG molecular dynamics simulation, while maintaining accuracy. Thus, our findings support the use of training objectives beyond FM, as a promising direction for improving CG NN potential\u2019s accuracy and reliability.<\/jats:p>","DOI":"10.1063\/5.0124538","type":"journal-article","created":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T15:34:00Z","timestamp":1669649640000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":47,"title":["Deep coarse-grained potentials via relative entropy minimization"],"prefix":"10.1063","volume":"157","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5383-1615","authenticated-orcid":false,"given":"Stephan","family":"Thaler","sequence":"first","affiliation":[{"name":"Multiscale Modeling of Fluid Materials, Department of Engineering Physics and Computation, TUM School of Engineering and Design, Technical University of Munich , Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1657-3060","authenticated-orcid":false,"given":"Maximilian","family":"Stupp","sequence":"additional","affiliation":[{"name":"Multiscale Modeling of Fluid Materials, Department of Engineering Physics and Computation, TUM School of Engineering and Design, Technical University of Munich , Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4495-9956","authenticated-orcid":false,"given":"Julija","family":"Zavadlav","sequence":"additional","affiliation":[{"name":"Multiscale Modeling of Fluid Materials, Department of Engineering Physics and Computation, TUM School of Engineering and Design, Technical University of Munich , Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"317","published-online":{"date-parts":[[2022,12,28]]},"reference":[{"key":"2023081007362747500_c1","doi-asserted-by":"publisher","first-page":"9362","DOI":"10.1021\/ma981060g","article-title":"Mapping of explicit atom onto united atom potentials","volume":"31","year":"1998","journal-title":"Macromolecules"},{"key":"2023081007362747500_c2","doi-asserted-by":"publisher","first-page":"1624","DOI":"10.1002\/jcc.10307","article-title":"Deriving effective mesoscale potentials from atomistic simulations","volume":"24","year":"2003","journal-title":"J. Comput. Chem."},{"key":"2023081007362747500_c3","doi-asserted-by":"publisher","first-page":"7812","DOI":"10.1021\/jp071097f","article-title":"The MARTINI force field: Coarse grained model for biomolecular simulations","volume":"111","year":"2007","journal-title":"J. Phys. Chem. B"},{"key":"2023081007362747500_c4","doi-asserted-by":"publisher","first-page":"244114","DOI":"10.1063\/1.2938860","article-title":"The multiscale coarse-graining method. I. A rigorous bridge between atomistic and coarse-grained models","volume":"128","year":"2008","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c5","doi-asserted-by":"publisher","first-page":"144108","DOI":"10.1063\/1.2992060","article-title":"The relative entropy is fundamental to multiscale and inverse thermodynamic problems","volume":"129","year":"2008","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c6","doi-asserted-by":"publisher","first-page":"090901","DOI":"10.1063\/1.4818908","article-title":"Perspective: Coarse-grained models for biomolecular systems","volume":"139","year":"2013","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c7","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1002\/wcms.1169","article-title":"The power of coarse graining in biomolecular simulations","volume":"4","year":"2014","journal-title":"Wiley Interdiscip. Rev.: Comput. Mol. Sci."},{"key":"2023081007362747500_c8","doi-asserted-by":"publisher","first-page":"3774","DOI":"10.3390\/ijms20153774","article-title":"Recent advances in coarse-grained models for biomolecules and their applications","volume":"20","year":"2019","journal-title":"Int. J. Mol. Sci."},{"key":"2023081007362747500_c9","doi-asserted-by":"publisher","first-page":"146401","DOI":"10.1103\/physrevlett.98.146401","article-title":"Generalized neural-network representation of high-dimensional potential-energy surfaces","volume":"98","year":"2007","journal-title":"Phys. Rev. Lett."},{"key":"2023081007362747500_c10","doi-asserted-by":"publisher","first-page":"074106","DOI":"10.1063\/1.3553717","article-title":"Atom-centered symmetry functions for constructing high-dimensional neural network potentials","volume":"134","year":"2011","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c11","article-title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","volume-title":"Advances in Neural Information Processing Systems","year":"2017"},{"key":"2023081007362747500_c12","first-page":"1263","article-title":"Neural message passing for quantum chemistry","year":"2017"},{"key":"2023081007362747500_c13","article-title":"Directional message passing for molecular graphs"},{"key":"2023081007362747500_c14","unstructured":"J.\u2008Klicpera, S.\u2008Giri, J. T.\u2008Margraf, and S.\u2008G\u00fcnnemann, \u201cFast and uncertainty-aware directional message passing for non-equilibrium molecules,\u201d in Machine Learning for Molecules Workshop at NeurIPS (2020)."},{"key":"2023081007362747500_c15","doi-asserted-by":"publisher","first-page":"124111","DOI":"10.1063\/5.0021955","article-title":"OrbNet: Deep learning for quantum chemistry using symmetry-adapted atomic-orbital features","volume":"153","year":"2020","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c16","doi-asserted-by":"publisher","first-page":"053805","DOI":"10.1103\/physrevmaterials.5.053805","article-title":"Machine learning for metallurgy III: A neural network potential for Al-Mg-Si","volume":"5","year":"2021","journal-title":"Phys. Rev. Mater."},{"key":"2023081007362747500_c17","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1038\/s41467-020-20427-2","article-title":"A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer","volume":"12","year":"2021","journal-title":"Nat. Commun."},{"key":"2023081007362747500_c18","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1038\/s41467-022-29939-5","article-title":"E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials","volume":"13","year":"2022","journal-title":"Nat. Commun."},{"key":"2023081007362747500_c19","unstructured":"I.\u2008Batatia, D. P.\u2008Kov\u00e1cs, G. N.\u2008Simm, C.\u2008Ortner, and G.\u2008Cs\u00e1nyi, \u201cMACE: Higher order equivariant message passing neural networks for fast and accurate force fields,\u201d arXiv:2206.07697 (2022)."},{"key":"2023081007362747500_c20","doi-asserted-by":"publisher","first-page":"034101","DOI":"10.1063\/1.5027645","article-title":"DeePCG: Constructing coarse-grained models via deep neural networks","volume":"149","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c21","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1021\/acscentsci.8b00913","article-title":"Machine learning of coarse-grained molecular dynamics force fields","volume":"5","year":"2019","journal-title":"ACS Cent. Sci."},{"key":"2023081007362747500_c22","doi-asserted-by":"publisher","first-page":"902","DOI":"10.1039\/c9me00184k","article-title":"Active learning a coarse-grained neural network model for bulk water from sparse training data","volume":"5","year":"2020","journal-title":"Mol. Syst. Des. Eng."},{"key":"2023081007362747500_c23","doi-asserted-by":"publisher","first-page":"194101","DOI":"10.1063\/5.0026133","article-title":"Coarse graining molecular dynamics with graph neural networks","volume":"153","year":"2020","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c24","doi-asserted-by":"publisher","first-page":"084101","DOI":"10.1063\/5.0059915","article-title":"Machine learning implicit solvation for molecular dynamics","volume":"155","year":"2021","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c25","doi-asserted-by":"crossref","unstructured":"X.\u2008Ding and B.\u2008Zhang, \u201cContrastive learning of coarse-grained force fields,\u201d J. Chem. Theory Comput.\u200818(10), 6334\u20136344 (2022).10.1021\/acs.jctc.2c00616","DOI":"10.1021\/acs.jctc.2c00616"},{"key":"2023081007362747500_c26","unstructured":"J.\u2008K\u00f6hler, Y.\u2008Chen, A.\u2008Kr\u00e4mer, C.\u2008Clementi, and F.\u2008No\u00e9, \u201cForce-matching coarse-graining without forces,\u201d arXiv:2203.11167 (2022)."},{"key":"2023081007362747500_c27","doi-asserted-by":"publisher","first-page":"6884","DOI":"10.1038\/s41467-021-27241-4","article-title":"Learning neural network potentials from experimental data via differentiable trajectory reweighting","volume":"12","year":"2021","journal-title":"Nat. Commun."},{"key":"2023081007362747500_c28","unstructured":"I.\u2008Batatia, S.\u2008Batzner, D. P.\u2008Kov\u00e1cs, A.\u2008Musaelian, G. N.\u2008Simm, R.\u2008Drautz, C.\u2008Ortner, B.\u2008Kozinsky, and G.\u2008Cs\u00e1nyi, \u201cThe design space of E(3)-equivariant atom-centered interatomic potentials,\u201d arXiv:2205.06643 (2022)."},{"key":"2023081007362747500_c29","doi-asserted-by":"publisher","first-page":"241710","DOI":"10.1063\/1.5020067","article-title":"Metadynamics for training neural network model chemistries: A competitive assessment","volume":"148","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c30","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","year":"2010"},{"key":"2023081007362747500_c31","doi-asserted-by":"publisher","first-page":"8383","DOI":"10.1021\/jp2114994","article-title":"A new multiscale algorithm and its application to coarse-grained peptide models for self-assembly","volume":"116","year":"2012","journal-title":"J. Phys. Chem. B"},{"key":"2023081007362747500_c32","doi-asserted-by":"publisher","first-page":"5641","DOI":"10.1021\/ct400730n","article-title":"Variational optimization of an all-atom implicit solvent force field to match explicit solvent simulation data","volume":"9","year":"2013","journal-title":"J. Chem. Theory Comput."},{"key":"2023081007362747500_c33","doi-asserted-by":"publisher","first-page":"e0131754","DOI":"10.1371\/journal.pone.0131754","article-title":"Relative entropy and optimization-driven coarse-graining methods in VOTCA","volume":"10","year":"2015","journal-title":"PLoS One"},{"key":"2023081007362747500_c34","doi-asserted-by":"publisher","first-page":"5678","DOI":"10.1021\/acs.jpcb.7b12446","article-title":"Transferable coarse-grained models of liquid\u2013liquid equilibrium using local density potentials optimized with the relative entropy","volume":"122","year":"2018","journal-title":"J. Phys. Chem. B"},{"key":"2023081007362747500_c35","doi-asserted-by":"publisher","first-page":"094112","DOI":"10.1063\/1.3557038","article-title":"Coarse-graining errors and numerical optimization using a relative entropy framework","volume":"134","year":"2011","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c36","doi-asserted-by":"publisher","first-page":"134105","DOI":"10.1063\/1.2038787","article-title":"Multiscale coarse graining of liquid-state systems","volume":"123","year":"2005","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c37","doi-asserted-by":"publisher","first-page":"244115","DOI":"10.1063\/1.2938857","article-title":"The multiscale coarse-graining method. II. Numerical implementation for coarse-grained molecular models","volume":"128","year":"2008","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c38","doi-asserted-by":"publisher","first-page":"198104","DOI":"10.1103\/physrevlett.103.198104","article-title":"Generalized Yvon-Born-Green theory for molecular systems","volume":"103","year":"2009","journal-title":"Phys. Rev. Lett."},{"key":"2023081007362747500_c39","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1039\/b818512c","article-title":"Anomalous waterlike behavior in spherically-symmetric water models optimized with the relative entropy","volume":"11","year":"2009","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2023081007362747500_c40","doi-asserted-by":"publisher","first-page":"060104","DOI":"10.1103\/PhysRevE.81.060104","article-title":"Relative entropy as a universal metric for multiscale errors","volume":"81","year":"2010","journal-title":"Phys. Rev. E"},{"key":"2023081007362747500_c41","doi-asserted-by":"publisher","first-page":"10538","DOI":"10.1039\/c0cp02826f","article-title":"Obtaining fully dynamic coarse-grained models from MD","volume":"13","year":"2011","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2023081007362747500_c42","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1002\/9781119290971.ch5","article-title":"Coarse-graining with the relative entropy","volume":"161","year":"2016","journal-title":"Adv. Chem. Phys."},{"key":"2023081007362747500_c43","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.jcp.2016.03.021","article-title":"Path-space variational inference for non-equilibrium coarse-grained systems","volume":"314","year":"2016","journal-title":"J. Comput. Phys."},{"key":"2023081007362747500_c44","doi-asserted-by":"publisher","first-page":"084105","DOI":"10.1063\/1.4928857","article-title":"The geometry of generalized force matching and related information metrics in coarse-graining of molecular systems","volume":"143","year":"2015","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c45","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"2023081007362747500_c46","doi-asserted-by":"publisher","first-page":"214101","DOI":"10.1063\/1.3663709","article-title":"Coarse-graining entropy, forces, and structures","volume":"135","year":"2011","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c47","doi-asserted-by":"publisher","first-page":"2087","DOI":"10.1021\/acs.jctc.5b00099","article-title":"Big data meets quantum chemistry approximations: The \u0394-machine learning approach","volume":"11","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"2023081007362747500_c48","doi-asserted-by":"publisher","first-page":"1442","DOI":"10.1021\/acs.jctc.7b01195","article-title":"Molecular dynamics simulations with quantum mechanics\/molecular mechanics and adaptive neural networks","volume":"14","year":"2018","journal-title":"J. Chem. Theory Comput."},{"key":"2023081007362747500_c49","doi-asserted-by":"publisher","first-page":"2641","DOI":"10.1021\/acs.jctc.0c01112","article-title":"Machine learning in QM\/MM molecular dynamics simulations of condensed-phase systems","volume":"17","year":"2021","journal-title":"J. Chem. Theory Comput."},{"key":"2023081007362747500_c50","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1140\/epje\/i2008-10413-5","article-title":"Comparative atomistic and coarse-grained study of water: What do we lose by coarse-graining?","volume":"28","year":"2009","journal-title":"Eur. Phys. J. E"},{"key":"2023081007362747500_c51","doi-asserted-by":"publisher","first-page":"2271","DOI":"10.1103\/physreve.50.2271","article-title":"Hamiltonians for discrete dynamics","volume":"50","year":"1994","journal-title":"Phys. Rev. E"},{"key":"2023081007362747500_c52","doi-asserted-by":"publisher","first-page":"224106","DOI":"10.1063\/1.4836615","article-title":"Ensemble simulations with discrete classical dynamics","volume":"139","year":"2013","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c53","doi-asserted-by":"publisher","first-page":"234505","DOI":"10.1063\/1.2121687","article-title":"A general purpose model for the condensed phases of water: TIP4P\/2005","volume":"123","year":"2005","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c54","first-page":"331","article-title":"Interaction models for water in relation to protein hydration","volume-title":"Intermolecular Forces","year":"1981"},{"key":"2023081007362747500_c55","doi-asserted-by":"publisher","first-page":"065502","DOI":"10.1103\/PhysRevLett.101.065502","article-title":"Quantum differences between heavy and light water","volume":"101","year":"2008","journal-title":"Phys. Rev. Lett."},{"key":"2023081007362747500_c56","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1103\/physreva.42.849","article-title":"Three-particle contribution to the configurational entropy of simple fluids","volume":"42","year":"1990","journal-title":"Phys. Rev. A"},{"key":"2023081007362747500_c57","doi-asserted-by":"publisher","first-page":"5882","DOI":"10.1063\/1.467100","article-title":"Triplet correlation functions for hard-spheres: Computer simulation results","volume":"100","year":"1994","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c58","doi-asserted-by":"publisher","first-page":"174504","DOI":"10.1063\/1.4898755","article-title":"Triplet correlation functions in liquid water","volume":"141","year":"2014","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c59","doi-asserted-by":"publisher","first-page":"3211","DOI":"10.1021\/ct900369w","article-title":"Versatile object-oriented toolkit for coarse-graining applications","volume":"5","year":"2009","journal-title":"J. Chem. Theory Comput."},{"key":"2023081007362747500_c60","doi-asserted-by":"publisher","first-page":"22387","DOI":"10.1039\/c8cp00746b","article-title":"Understanding three-body contributions to coarse-grained force fields","volume":"20","year":"2018","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2023081007362747500_c61","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1140\/epjst\/e2016-60145-x","article-title":"Parametrizing coarse grained models for molecular systems at equilibrium","volume":"225","year":"2016","journal-title":"Eur. Phys. J.: Spec. Top."},{"key":"2023081007362747500_c62","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/0009-2614(85)85509-3","article-title":"The potential of mean force surface for the alanine dipeptide in aqueous solution: A theoretical approach","volume":"121","year":"1985","journal-title":"Chem. Phys. Lett."},{"key":"2023081007362747500_c63","doi-asserted-by":"publisher","first-page":"3864","DOI":"10.1021\/j100188a054","article-title":"Conformational equilibrium in the alanine dipeptide in the gas phase and aqueous solution: A comparison of theoretical results","volume":"96","year":"1992","journal-title":"J. Phys. Chem."},{"key":"2023081007362747500_c64","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1002\/jcc.10349","article-title":"A point-charge force field for molecular mechanics simulations of proteins based on condensed-phase quantum mechanical calculations","volume":"24","year":"2003","journal-title":"J. Comput. Chem."},{"key":"2023081007362747500_c65","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.sbi.2008.01.003","article-title":"Recent advances in implicit solvent-based methods for biomolecular simulations","volume":"18","year":"2008","journal-title":"Curr. Opin. Struct. Biol."},{"key":"2023081007362747500_c66","doi-asserted-by":"publisher","first-page":"1420","DOI":"10.1063\/1.1740409","article-title":"High-temperature equation of state by a perturbation method. I. Nonpolar gases","volume":"22","year":"1954","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c67","volume-title":"Free Energy Calculations","year":"2007"},{"key":"2023081007362747500_c68","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1529\/biophysj.107.108241","article-title":"Experimental parameterization of an energy function for the simulation of unfolded proteins","volume":"94","year":"2008","journal-title":"Biophys. J."},{"key":"2023081007362747500_c69","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1021\/ct200094b","article-title":"Iterative optimization of molecular mechanics force fields from NMR data of full-length proteins","volume":"7","year":"2011","journal-title":"J. Chem. Theory Comput."},{"key":"2023081007362747500_c70","unstructured":"S. R.\u2008Xie, M.\u2008Rupp, and R. G.\u2008Hennig, \u201cUltra-fast interpretable machine-learning potentials,\u201d arXiv:2110.00624 (2021)."},{"key":"2023081007362747500_c71","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1002\/wcms.31","article-title":"Metadynamics","volume":"1","year":"2011","journal-title":"Wiley Interdiscip. Rev.: Comput. Mol. Sci."},{"key":"2023081007362747500_c72","doi-asserted-by":"publisher","first-page":"265701","DOI":"10.1103\/physrevlett.121.265701","article-title":"Silicon liquid structure and crystal nucleation from ab initio deep metadynamics","volume":"121","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"2023081007362747500_c73","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/0009-2614(89)87263-x","article-title":"Anharmonic force fields from analytic second derivatives: Method and application to methyl bromide","volume":"157","year":"1989","journal-title":"Chem. Phys. Lett."},{"key":"2023081007362747500_c74","doi-asserted-by":"publisher","first-page":"3309","DOI":"10.1021\/acs.jpclett.5b01456","article-title":"Machine learning for quantum mechanical properties of atoms in molecules","volume":"6","year":"2015","journal-title":"J. Phys. Chem. Lett."},{"key":"2023081007362747500_c75","doi-asserted-by":"publisher","first-page":"045010","DOI":"10.1088\/2632-2153\/ac9955","article-title":"How robust are modern graph neural network potentials in long and hot molecular dynamics simulations?","volume":"3","year":"2022","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"2023081007362747500_c76","unstructured":"X.\u2008Fu, Z.\u2008Wu, W.\u2008Wang, T.\u2008Xie, S.\u2008Keten, R.\u2008Gomez-Bombarelli, and T.\u2008Jaakkola, \u201cForces are not enough: Benchmark and critical evaluation for machine learning force fields with molecular simulations,\u201d arXiv:2210.07237 (2022)."},{"key":"2023081007362747500_c77","doi-asserted-by":"publisher","first-page":"241733","DOI":"10.1063\/1.5023802","article-title":"Less is more: Sampling chemical space with active learning","volume":"148","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2023081007362747500_c78","doi-asserted-by":"publisher","first-page":"023804","DOI":"10.1103\/physrevmaterials.3.023804","article-title":"Active learning of uniformly accurate interatomic potentials for materials simulation","volume":"3","year":"2019","journal-title":"Phys. Rev. Mater."},{"key":"2023081007362747500_c79","doi-asserted-by":"publisher","first-page":"6946","DOI":"10.1021\/acs.jpclett.0c01061","article-title":"On-the-fly active learning of interatomic potentials for large-scale atomistic simulations","volume":"11","year":"2020","journal-title":"J. Phys. Chem. Lett."},{"key":"2023081007362747500_c80","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1038\/s41467-021-21376-0","article-title":"Automated discovery of a robust interatomic potential for aluminum","volume":"12","year":"2021","journal-title":"Nat. Commun."},{"key":"2023081007362747500_c81","article-title":"Learning protein structure with a differentiable simulator"},{"key":"2023081007362747500_c82","article-title":"JAX, M.D.: A framework for differentiable physics","volume-title":"Advances in Neural Information Processing Systems","year":"2020"},{"key":"2023081007362747500_c83","doi-asserted-by":"publisher","first-page":"e2024083118","DOI":"10.1073\/pnas.2024083118","article-title":"Designing self-assembling kinetics with differentiable statistical physics models","volume":"118","year":"2021","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"2023081007362747500_c84","doi-asserted-by":"publisher","first-page":"2355","DOI":"10.1021\/acs.jctc.0c01343","article-title":"TorchMD: A deep learning framework for molecular simulations","volume":"17","year":"2021","journal-title":"J. Chem. Theory Comput."}],"container-title":["The Journal of Chemical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0124538\/16556054\/244103_1_online.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0124538\/16556054\/244103_1_online.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T09:44:02Z","timestamp":1691660642000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jcp\/article\/157\/24\/244103\/2842894\/Deep-coarse-grained-potentials-via-relative"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,28]]},"references-count":84,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2022,12,28]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0124538","relation":{},"ISSN":["0021-9606","1089-7690"],"issn-type":[{"value":"0021-9606","type":"print"},{"value":"1089-7690","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,12,28]]},"published":{"date-parts":[[2022,12,28]]},"article-number":"244103"}}