{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T22:34:41Z","timestamp":1784673281997,"version":"3.55.0"},"reference-count":102,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T00:00:00Z","timestamp":1724198400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T00:00:00Z","timestamp":1724198400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000893","name":"Simons Foundation","doi-asserted-by":"crossref","award":["454933"],"award-info":[{"award-number":["454933"]}],"id":[{"id":"10.13039\/100000893","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":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Normalizing flows can transform a simple prior probability distribution into a more complex target distribution. Here, we evaluate the ability and efficiency of generative machine learning methods to sample the Boltzmann distribution of an atomistic model for glass-forming liquids. This is a notoriously difficult task, as it amounts to ergodically exploring the complex free energy landscape of a disordered and frustrated many-body system. We optimize a normalizing flow model to successfully transform high-temperature configurations of a dense liquid into low-temperature ones, near the glass transition. We perform a detailed comparative analysis with established enhanced sampling techniques developed in the physics literature to assess and rank the performance of normalizing flows against state-of-the-art algorithms. We demonstrate that machine learning methods are very promising, showing a large speedup over conventional molecular dynamics. Normalizing flows show performances comparable to parallel tempering and population annealing, while still falling far behind the swap Monte Carlo algorithm. Our study highlights the potential of generative machine learning models in scientific computing for complex systems, but also points to some of its current limitations and the need for further improvement.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad6ca0","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T22:57:00Z","timestamp":1723071420000},"page":"035053","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Normalizing flows as an enhanced sampling method for atomistic supercooled liquids"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6739-1603","authenticated-orcid":true,"given":"Gerhard","family":"Jung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giulio","family":"Biroli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2059-702X","authenticated-orcid":true,"given":"Ludovic","family":"Berthier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2024,8,21]]},"reference":[{"key":"mlstad6ca0bib1","doi-asserted-by":"publisher","author":"Battimelli","year":"2020","DOI":"10.1007\/978-3-030-39399-1"},{"key":"mlstad6ca0bib2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-267351-1.X5000-7","volume":"vol 1","author":"Frenkel","year":"2001","journal-title":"Understanding Molecular Simulation: From Algorithms to Applications"},{"key":"mlstad6ca0bib3","doi-asserted-by":"publisher","author":"Allen","year":"2017","DOI":"10.1093\/oso\/9780198803195.001.0001"},{"key":"mlstad6ca0bib4","doi-asserted-by":"publisher","author":"Newman","year":"1999","DOI":"10.1007\/978-3-642-82803-4"},{"key":"mlstad6ca0bib5","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1063\/1.1699114","article-title":"equation of state calculations by fast computing machines","volume":"21","author":"Metropolis","year":"1953","journal-title":"J. Chem. Phys."},{"key":"mlstad6ca0bib6","doi-asserted-by":"publisher","author":"Hastings","year":"1970","DOI":"10.2307\/2334940"},{"key":"mlstad6ca0bib7","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1063\/1.1743957","article-title":"Phase transition for a hard sphere system","volume":"27","author":"Alder","year":"1957","journal-title":"J. Chem. Phys."},{"key":"mlstad6ca0bib8","doi-asserted-by":"publisher","first-page":"3336","DOI":"10.1063\/1.1676585","article-title":"Molecular dynamics study of liquid water","volume":"55","author":"Rahman","year":"1971","journal-title":"J. Chem. Phys."},{"key":"mlstad6ca0bib9","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198515357.001.0001","volume":"vol 13","author":"Krauth","year":"2006","journal-title":"Statistical Mechanics: Algorithms and Computations"},{"key":"mlstad6ca0bib10","doi-asserted-by":"publisher","author":"Landau","year":"2021","DOI":"10.1017\/CBO9781139696463"},{"key":"mlstad6ca0bib11","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/0009-2614(89)87505-0","article-title":"Equation of state for symmetric non-additive hard-sphere fluids: an approximate analytic expression and new Monte Carlo results","volume":"159","author":"Gazzillo","year":"1989","journal-title":"Chem. Phys. Lett."},{"key":"mlstad6ca0bib12","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1080\/00268979100100501","article-title":"Computer simulation of solid-liquid coexistence in binary hard sphere mixtures","volume":"72","author":"Kranendonk","year":"1991","journal-title":"Mol. Phys."},{"key":"mlstad6ca0bib13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.63.045102","article-title":"Fast Monte Carlo algorithm for supercooled soft spheres","volume":"63","author":"Grigera","year":"2001","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib14","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1119\/1.4961596","article-title":"Lifting\u2014a nonreversible Markov chain Monte Carlo algorithm","volume":"84","author":"Vucelja","year":"2016","journal-title":"Am. J. Phys."},{"key":"mlstad6ca0bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.80.056704","article-title":"Event-chain Monte Carlo algorithms for hard-sphere systems","volume":"80","author":"Bernard","year":"2009","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib16","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2021.663457","article-title":"Event-chain Monte Carlo: foundations, applications and prospects","volume":"9","author":"Krauth","year":"2021","journal-title":"Front. Phys."},{"key":"mlstad6ca0bib17","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevLett.133.028202","article-title":"Irreversible Monte Carlo algorithms for hard disk glasses: from event-chain to collective swaps","author":"Ghimenti","year":"2024"},{"key":"mlstad6ca0bib18","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1209\/0295-5075\/19\/6\/002","article-title":"Simulated tempering: a new Monte Carlo scheme","volume":"19","author":"Marinari","year":"1992","journal-title":"Europhys. Lett."},{"key":"mlstad6ca0bib19","doi-asserted-by":"publisher","first-page":"1604","DOI":"10.1143\/JPSJ.65.1604","article-title":"Exchange Monte Carlo method and application to spin glass simulations","volume":"65","author":"Hukushima","year":"1996","journal-title":"J. Phys. Soc. Japan"},{"key":"mlstad6ca0bib20","doi-asserted-by":"publisher","first-page":"3910","DOI":"10.1039\/b509983h","article-title":"Parallel tempering: theory, applications and new perspectives","volume":"7","author":"Earl","year":"2005","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstad6ca0bib21","doi-asserted-by":"publisher","first-page":"2607","DOI":"10.1103\/PhysRevLett.57.2607","article-title":"Replica Monte Carlo simulation of spin-glasses","volume":"57","author":"Swendsen","year":"1986","journal-title":"Phys. Rev. Lett."},{"key":"mlstad6ca0bib22","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1063\/1.1632130","article-title":"Population annealing and its application to a spin glass","volume":"690","author":"Hukushima","year":"2003","journal-title":"AIP Conf. Proc."},{"key":"mlstad6ca0bib23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.82.026704","article-title":"Population annealing with weighted averages: a Monte Carlo method for rough free-energy landscapes","volume":"82","author":"Machta","year":"2010","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.97.033301","article-title":"Analysis and optimization of population annealing","volume":"97","author":"Amey","year":"2018","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.131.257101","article-title":"Sampling efficiency of transverse forces in dense liquids","volume":"131","author":"Ghimenti","year":"2023","journal-title":"Phys. Rev. Lett."},{"key":"mlstad6ca0bib26","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1103\/RevModPhys.83.587","article-title":"Theoretical perspective on the glass transition and amorphous materials","volume":"83","author":"Berthier","year":"2011","journal-title":"Rev. Mod. Phys."},{"key":"mlstad6ca0bib27","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1038\/s42254-022-00548-x","article-title":"Modern computational studies of the glass transition","volume":"5","author":"Berthier","year":"2023","journal-title":"Nat. Rev. Phys."},{"key":"mlstad6ca0bib28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5802\/crphys.129","article-title":"Computer simulations of the glass transition and glassy materials","volume":"24","author":"Barrat","year":"2023","journal-title":"C. R. Physique"},{"key":"mlstad6ca0bib29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.2661","article-title":"Generative adversarial nets","volume":"vol 27","author":"Goodfellow","year":"2014"},{"key":"mlstad6ca0bib30","first-page":"pp 2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015"},{"key":"mlstad6ca0bib31","first-page":"p 6840","article-title":"Denoising diffusion probabilistic models","volume":"vol 33","author":"Ho","year":"2020"},{"key":"mlstad6ca0bib32","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"mlstad6ca0bib33","first-page":"pp 1530","article-title":"Variational inference with normalizing flows","author":"Rezende","year":"2015"},{"key":"mlstad6ca0bib34","doi-asserted-by":"publisher","first-page":"eaaw1147","DOI":"10.1126\/science.aaw1147","article-title":"Boltzmann generators: sampling equilibrium states of many-body systems with deep learning","volume":"365","author":"No\u00e9","year":"2019","journal-title":"Science"},{"key":"mlstad6ca0bib35","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.122.080602","article-title":"Solving statistical mechanics using variational autoregressive networks","volume":"122","author":"Wu","year":"2019","journal-title":"Phys. Rev. Lett."},{"key":"mlstad6ca0bib36","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpclett.2c03327","article-title":"Skipping the replica exchange ladder with normalizing flows","volume":"13","author":"Invernizzi","year":"2022","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstad6ca0bib37","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2109420119","article-title":"Adaptive Monte Carlo augmented with normalizing flows","volume":"119","author":"Gabri\u00e9","year":"2022","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstad6ca0bib38","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acf55c","article-title":"Conditioning Boltzmann generators for rare event sampling","volume":"4","author":"Falkner","year":"2023","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad6ca0bib39","article-title":"Learning mappings between equilibrium states of liquid systems using normalizing flows","author":"Coretti","year":"2022"},{"key":"mlstad6ca0bib40","article-title":"A Boltzmann generator for the isobaric-isothermal ensemble","author":"van Leeuwen","year":"2023"},{"key":"mlstad6ca0bib41","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpcb.0c08645","article-title":"Computing absolute free energy with deep generative models","volume":"124","author":"Ding","year":"2020","journal-title":"J. Phys. Chem. B"},{"key":"mlstad6ca0bib42","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acefa8","article-title":"Estimating Gibbs free energies via isobaric-isothermal flows","volume":"4","author":"Wirnsberger","year":"2023","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad6ca0bib43","article-title":"Wavelet conditional renormalization group","author":"Marchand","year":"2022"},{"key":"mlstad6ca0bib44","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.107.014512","article-title":"Conditional normalizing flow for Markov chain Monte Carlo sampling in the critical region of lattice field theory","volume":"107","author":"Singha","year":"2023","journal-title":"Phys. Rev. D"},{"key":"mlstad6ca0bib45","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.101.053312","article-title":"Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks","volume":"101","author":"McNaughton","year":"2020","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib46","doi-asserted-by":"publisher","first-page":"018","DOI":"10.21468\/SciPostPhys.15.1.018","article-title":"Accelerating equilibrium spin-glass simulations using quantum annealers via generative deep learning","volume":"15","author":"Scriva","year":"2023","journal-title":"SciPost Phys."},{"key":"mlstad6ca0bib47","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acbe91","article-title":"Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems","volume":"4","author":"Ciarella","year":"2023","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad6ca0bib48","article-title":"Sampling with flows, diffusion and autoregressive neural networks: a spin-glass perspective","author":"Ghio","year":"2023"},{"key":"mlstad6ca0bib49","doi-asserted-by":"publisher","author":"Mezard","year":"2009","DOI":"10.1093\/acprof:oso\/9780198570837.001.0001"},{"key":"mlstad6ca0bib50","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1038\/srep00329","article-title":"Detection of hidden structures for arbitrary scales in complex physical systems","volume":"2","author":"Ronhovde","year":"2012","journal-title":"Sci. Rep."},{"key":"mlstad6ca0bib51","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1038\/nphys3644","article-title":"A structural approach to relaxation in glassy liquids","volume":"12","author":"Schoenholz","year":"2016","journal-title":"Nat. Phys."},{"key":"mlstad6ca0bib52","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1038\/s41567-020-0842-8","article-title":"Unveiling the predictive power of static structure in glassy systems","volume":"16","author":"Bapst","year":"2020","journal-title":"Nat. Phys."},{"key":"mlstad6ca0bib53","doi-asserted-by":"publisher","DOI":"10.1063\/5.0004732","article-title":"Assessing the structural heterogeneity of supercooled liquids through community inference","volume":"152","author":"Paret","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstad6ca0bib54","article-title":"Roadmap on machine learning glassy liquids","author":"Jung","year":"2023"},{"key":"mlstad6ca0bib55","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.12.041028","article-title":"Thirty milliseconds in the life of a supercooled liquid","volume":"12","author":"Scalliet","year":"2022","journal-title":"Phys. Rev. X"},{"key":"mlstad6ca0bib56","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.130.238202","article-title":"Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning","volume":"130","author":"Jung","year":"2023","journal-title":"Phys. Rev. Lett."},{"key":"mlstad6ca0bib57","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.109.064205","article-title":"Dynamic heterogeneity at the experimental glass transition predicted by transferable machine learning","volume":"109","author":"Jung","year":"2024","journal-title":"Phys. Rev. B"},{"key":"mlstad6ca0bib58","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.7.021039","article-title":"Models and algorithms for the next generation of glass transition studies","volume":"7","author":"Ninarello","year":"2017","journal-title":"Phys. Rev. X"},{"key":"mlstad6ca0bib59","doi-asserted-by":"publisher","first-page":"4626","DOI":"10.1103\/PhysRevE.51.4626","article-title":"Testing mode-coupling theory for a supercooled binary Lennard-Jones mixture I: the van Hove correlation function","volume":"51","author":"Kob","year":"1995","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib60","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.125.085505","article-title":"Ultrastable metallic glasses in silico","volume":"125","author":"Parmar","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstad6ca0bib61","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/20\/37\/373101","article-title":"Exploring the potential energy landscape of glass-forming systems: from inherent structures via metabasins to macroscopic transport","volume":"20","author":"Heuer","year":"2008","journal-title":"J. Phys.: Condens. Matter"},{"key":"mlstad6ca0bib62","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.116.238002","article-title":"Equilibrium sampling of hard spheres up to the jamming density and beyond","volume":"116","author":"Berthier","year":"2016","journal-title":"Phys. Rev. Lett."},{"key":"mlstad6ca0bib63","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab1910","article-title":"Efficient swap algorithms for molecular dynamics simulations of equilibrium supercooled liquids","author":"Berthier","year":"2019","journal-title":"J. Stat. Mech."},{"key":"mlstad6ca0bib64","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.73.061505","article-title":"Hybrid Monte Carlo simulation of a glass-forming binary mixture","volume":"73","author":"Flenner","year":"2006","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib65","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/S0009-2614(99)01123-9","article-title":"Replica-exchange molecular dynamics method for protein folding","volume":"314","author":"Sugita","year":"1999","journal-title":"Chem. Phys. Lett."},{"key":"mlstad6ca0bib66","doi-asserted-by":"publisher","DOI":"10.1021\/ja062463w","article-title":"Free-energy landscape for \u03b2 hairpin folding from combined parallel tempering and metadynamics","volume":"128","author":"Bussi","year":"2006","journal-title":"J. Am. Chem. Soc."},{"key":"mlstad6ca0bib67","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.63.016701","article-title":"Parallel excluded volume tempering for polymer melts","volume":"63","author":"Bunker","year":"2000","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib68","doi-asserted-by":"publisher","first-page":"1754","DOI":"10.1063\/1.477812","article-title":"A biased Monte Carlo scheme for zeolite structure solution","volume":"110","author":"Falcioni","year":"1999","journal-title":"J. Chem. Phys."},{"key":"mlstad6ca0bib69","doi-asserted-by":"publisher","first-page":"5473","DOI":"10.1103\/PhysRevE.61.5473","article-title":"Replica-exchange molecular dynamics simulation for supercooled liquids","volume":"61","author":"Yamamoto","year":"2000","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib70","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.65.051202","article-title":"Equilibration times in numerical simulation of structural glasses: comparing parallel tempering and conventional molecular dynamics","volume":"65","author":"De Michele","year":"2002","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib71","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.94.032605","article-title":"Point-to-set lengths, local structure and glassiness","volume":"94","author":"Yaida","year":"2016","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib72","doi-asserted-by":"publisher","DOI":"10.1063\/1.4939640","article-title":"Efficient measurement of point-to-set correlations and overlap fluctuations in glass-forming liquids","volume":"144","author":"Berthier","year":"2016","journal-title":"J. Chem. Phys."},{"key":"mlstad6ca0bib73","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.110.245702","article-title":"Probing a liquid to glass transition in equilibrium","volume":"110","author":"Kob","year":"2013","journal-title":"Phys. Rev. Lett."},{"key":"mlstad6ca0bib74","doi-asserted-by":"publisher","first-page":"2635","DOI":"10.1103\/PhysRevLett.61.2635","article-title":"New Monte Carlo technique for studying phase transitions","volume":"61","author":"Ferrenberg","year":"1988","journal-title":"Phys. Rev. Lett."},{"key":"mlstad6ca0bib75","doi-asserted-by":"publisher","DOI":"10.1063\/1.2944250","article-title":"A statistical analysis of the precision of reweighting-based simulations","volume":"129","author":"Shen","year":"2008","journal-title":"J. Chem. Phys."},{"key":"mlstad6ca0bib76","doi-asserted-by":"publisher","first-page":"2677","DOI":"10.1021\/ct500090q","article-title":"Improved reweighting of accelerated molecular dynamics simulations for free energy calculation","volume":"10","author":"Miao","year":"2014","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad6ca0bib77","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1002\/wics.56","article-title":"Importance sampling: a review","volume":"2","author":"Tokdar","year":"2010","journal-title":"Wiley Interdiscip. Rev. Comput. Stat."},{"key":"mlstad6ca0bib78","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.92.063307","article-title":"Population annealing: theory and application in spin glasses","volume":"92","author":"Wang","year":"2015","journal-title":"Phys. Rev. E"},{"key":"mlstad6ca0bib79","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevE.108.065309","article-title":"Resampling schemes in population annealing\u2013numerical and theoretical results","author":"Gessert","year":"2023"},{"key":"mlstad6ca0bib80","first-page":"1","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"mlstad6ca0bib81","article-title":"Density estimation using real NVP","author":"Dinh","year":"2016"},{"key":"mlstad6ca0bib82","article-title":"A-NICE-MC: adversarial training for MCMC","volume":"vol 30","author":"Song","year":"2017"},{"key":"mlstad6ca0bib83","article-title":"Timewarp: transferable acceleration of molecular dynamics by learning time-coarsened dynamics","volume":"vol 36","author":"Klein","year":"2024"},{"key":"mlstad6ca0bib84","article-title":"Introduction to normalizing flows for lattice field theory","author":"Albergo","year":"2021"},{"key":"mlstad6ca0bib85","first-page":"pp 5361","article-title":"Equivariant flows: exact likelihood generative learning for symmetric densities","author":"K\u00f6hler","year":"2020"},{"key":"mlstad6ca0bib86","article-title":"Usually this transformation is defined as T, see [85], which we avoid due to the importance of the temperature T in the present study"},{"key":"mlstad6ca0bib87","article-title":"Flow annealed importance sampling bootstrap","author":"Midgley","year":"2023"},{"key":"mlstad6ca0bib88","author":"Kish","year":"1965"},{"key":"mlstad6ca0bib89","article-title":"Measuring glass entropies with population annealing","author":"Amey","year":"2021"},{"key":"mlstad6ca0bib90","article-title":"SE(3) equivariant augmented coupling flows","author":"Midgley","year":"2023"},{"key":"mlstad6ca0bib91","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023"},{"key":"mlstad6ca0bib92","article-title":"Equivariant flow matching","author":"Klein","year":"2023"},{"key":"mlstad6ca0bib93","article-title":"Designing losses for data-free training of normalizing flows on Boltzmann distributions","author":"Felardos","year":"2023"},{"key":"mlstad6ca0bib94","first-page":"pp 318","article-title":"Annealed flow transport Monte Carlo","author":"Arbel","year":"2021"},{"key":"mlstad6ca0bib95","article-title":"GeoDiff: a geometric diffusion model for molecular conformation generation","author":"Xu","year":"2022"},{"key":"mlstad6ca0bib96","article-title":"Towards predicting equilibrium distributions for molecular systems with deep learning","author":"Zheng","year":"2023"},{"key":"mlstad6ca0bib97","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2023.111972","article-title":"A physics-informed diffusion model for high-fidelity flow field reconstruction","volume":"478","author":"Shu","year":"2023","journal-title":"J. Comput. Phys."},{"key":"mlstad6ca0bib98","first-page":"pp 5933","article-title":"Stochastic normalizing flows","volume":"vol 33","author":"Wu","year":"2020"},{"key":"mlstad6ca0bib99","first-page":"p 2628","article-title":"Deep probabilistic imaging: uncertainty quantification and multi-modal solution characterization for computational imaging","volume":"vol 35","author":"Sun","year":"2021"},{"key":"mlstad6ca0bib100","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"Higgins","year":"2017"},{"key":"mlstad6ca0bib101","doi-asserted-by":"publisher","DOI":"10.1063\/5.0029113","article-title":"Use the force! Reduced variance estimators for densities, radial distribution functions and local mobilities in molecular simulations","volume":"153","author":"Rotenberg","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstad6ca0bib102","doi-asserted-by":"publisher","DOI":"10.1063\/5.0039250","article-title":"Single-parameter aging in a binary Lennard-Jones system","volume":"154","author":"Mehri","year":"2021","journal-title":"J. Chem. Phys."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6ca0","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6ca0\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6ca0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6ca0\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6ca0\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6ca0\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6ca0\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6ca0\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T19:38:26Z","timestamp":1724355506000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6ca0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,21]]},"references-count":102,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,8,21]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad6ca0","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,21]]},"assertion":[{"value":"Normalizing flows as an enhanced sampling method for atomistic supercooled liquids","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":"2024-05-16","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-07","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-21","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}