{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T10:18:23Z","timestamp":1777803503806,"version":"3.51.4"},"reference-count":81,"publisher":"Proceedings of the National Academy of Sciences","issue":"17","license":[{"start":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T00:00:00Z","timestamp":1602201600000},"content-version":"vor","delay-in-days":183,"URL":"https:\/\/www.pnas.org\/site\/aboutpnas\/licenses.xhtml"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-1751636"],"award-info":[{"award-number":["DMS-1751636"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-1440415"],"award-info":[{"award-number":["DMS-1440415"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"DOD | USAF | AFMC | Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["MURI FA9550-18- 1-0502"],"award-info":[{"award-number":["MURI FA9550-18- 1-0502"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"DOD | USAF | AFMC | Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-18-1-0167"],"award-info":[{"award-number":["FA9550-18-1-0167"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007297","name":"DOD | United States Navy | ONR | Office of Naval Research Global","doi-asserted-by":"publisher","award":["N00014-18-1-2527"],"award-info":[{"award-number":["N00014-18-1-2527"]}],"id":[{"id":"10.13039\/100007297","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.pnas.org"],"crossmark-restriction":true},"short-container-title":["Proc. Natl. Acad. Sci. U.S.A."],"published-print":{"date-parts":[[2020,4,28]]},"abstract":"<jats:p>Mean field games (MFG) and mean field control (MFC) are critical classes of multiagent models for the efficient analysis of massive populations of interacting agents. Their areas of application span topics in economics, finance, game theory, industrial engineering, crowd motion, and more. In this paper, we provide a flexible machine learning framework for the numerical solution of potential MFG and MFC models. State-of-the-art numerical methods for solving such problems utilize spatial discretization that leads to a curse of dimensionality. We approximately solve high-dimensional problems by combining Lagrangian and Eulerian viewpoints and leveraging recent advances from machine learning. More precisely, we work with a Lagrangian formulation of the problem and enforce the underlying Hamilton\u2013Jacobi\u2013Bellman (HJB) equation that is derived from the Eulerian formulation. Finally, a tailored neural network parameterization of the MFG\/MFC solution helps us avoid any spatial discretization. Our numerical results include the approximate solution of 100-dimensional instances of optimal transport and crowd motion problems on a standard work station and a validation using a Eulerian solver in two dimensions. These results open the door to much-anticipated applications of MFG and MFC models that are beyond reach with existing numerical methods.<\/jats:p>","DOI":"10.1073\/pnas.1922204117","type":"journal-article","created":{"date-parts":[[2020,4,10]],"date-time":"2020-04-10T00:15:27Z","timestamp":1586477727000},"page":"9183-9193","update-policy":"https:\/\/doi.org\/10.1073\/pnas.cm10313","source":"Crossref","is-referenced-by-count":160,"title":["A machine learning framework for solving high-dimensional mean field game and mean field control problems"],"prefix":"10.1073","volume":"117","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0803-3299","authenticated-orcid":false,"given":"Lars","family":"Ruthotto","sequence":"first","affiliation":[{"name":"Department of Mathematics, Emory University, Atlanta, GA 30322;"},{"name":"Department of Computer Science, Emory University, Atlanta, GA 30322;"}]},{"given":"Stanley J.","family":"Osher","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of California, Los Angeles, CA 90095"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2218-5734","authenticated-orcid":false,"given":"Wuchen","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of California, Los Angeles, CA 90095"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6227-0941","authenticated-orcid":false,"given":"Levon","family":"Nurbekyan","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of California, Los Angeles, CA 90095"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2926-4582","authenticated-orcid":false,"given":"Samy Wu","family":"Fung","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of California, Los Angeles, CA 90095"}]}],"member":"341","published-online":{"date-parts":[[2020,4,9]]},"reference":[{"key":"e_1_3_4_1_2","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1016\/j.crma.2006.09.019","article-title":"Jeux \u00e0 champ moyen. I. Le cas stationnaire","volume":"343","author":"Lasry J.-M.","year":"2006","unstructured":"J.-M. Lasry, P.-L. Lions, Jeux \u00e0 champ moyen. I. Le cas stationnaire. C. R. Math. Acad. Sci. Paris 343, 619\u2013625 (2006).","journal-title":"C. R. Math. Acad. Sci. Paris"},{"key":"e_1_3_4_2_2","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1016\/j.crma.2006.09.018","article-title":"Jeux \u00e0 champ moyen. II. Horizon fini et contr\u00f4le optimal","volume":"343","author":"Lasry J.-M.","year":"2006","unstructured":"J.-M. Lasry, P.-L. Lions, Jeux \u00e0 champ moyen. II. Horizon fini et contr\u00f4le optimal. C. R. Math. Acad. Sci. Paris 343, 679\u2013684 (2006).","journal-title":"C. R. Math. Acad. Sci. Paris"},{"key":"e_1_3_4_3_2","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/s11537-007-0657-8","article-title":"Mean field games","volume":"2","author":"Lasry J.-M.","year":"2007","unstructured":"J.-M. Lasry, P.-L. Lions, Mean field games. Jpn. J. Math. 2, 229\u2013260 (2007).","journal-title":"Jpn. J. Math."},{"key":"e_1_3_4_4_2","doi-asserted-by":"crossref","first-page":"221","DOI":"10.4310\/CIS.2006.v6.n3.a5","article-title":"Large population stochastic dynamic games: Closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle","volume":"6","author":"Huang M.","year":"2006","unstructured":"M. Huang, R. P. Malham\u00e9, P. E. Caines, Large population stochastic dynamic games: Closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle. Commun. Inf. Syst. 6, 221\u2013251 (2006).","journal-title":"Commun. Inf. Syst."},{"key":"e_1_3_4_5_2","doi-asserted-by":"crossref","first-page":"1560","DOI":"10.1109\/TAC.2007.904450","article-title":"Large-population cost-coupled LQG problems with nonuniform agents: Individual-mass behavior and decentralized \u03f5-Nash equilibria","volume":"52","author":"Huang M.","year":"2007","unstructured":"M. Huang, P. E. Caines, R. P. Malham\u00e9, Large-population cost-coupled LQG problems with nonuniform agents: Individual-mass behavior and decentralized \u03f5-Nash equilibria. IEEE Trans. Autom. Control 52, 1560\u20131571 (2007).","journal-title":"IEEE Trans. Autom. Control"},{"key":"e_1_3_4_6_2","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-8508-7","volume-title":"Mean Field Games and Mean Field Type Control Theory","author":"Bensoussan A.","year":"2013","unstructured":"A. Bensoussan, J. Frehse, P. Yam, Mean Field Games and Mean Field Type Control Theory (Springer, New York, 2013)."},{"key":"e_1_3_4_7_2","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/978-3-642-14660-2_3","volume-title":"Paris-Princeton Lectures on Mathematical Finance 2010","author":"Gu\u00e9ant O.","year":"2011","unstructured":"O. Gu\u00e9ant, J.-M. Lasry, P.-L. Lions, \u201cMean field games and applications\u201d in Paris-Princeton Lectures on Mathematical Finance 2010, R. Carmona , Eds. (Lecture Notes in Mathematics, Springer, Berlin, 2011), vol. 2003, pp. 205\u2013266."},{"key":"e_1_3_4_8_2","doi-asserted-by":"crossref","first-page":"20130397","DOI":"10.1098\/rsta.2013.0397","article-title":"Partial differential equation models in macroeconomics","volume":"372","author":"Achdou Y.","year":"2014","unstructured":"Y. Achdou, F. J. Buera, J.-M. Lasry, P.-L. Lions, B. Moll, Partial differential equation models in macroeconomics. Philos. Trans. R. Soc. A 372, 20130397 (2014).","journal-title":"Philos. Trans. R. Soc. A"},{"key":"e_1_3_4_9_2","volume-title":"Economic Models and Mean-Field Games Theory","author":"Gomes D. A.","year":"2015","unstructured":"D. A. Gomes, L. Nurbekyan, E. A. Pimentel, Economic Models and Mean-Field Games Theory (Instituto Nacional de Matem\u00e1tica Pura e Aplicada, Rio de Janeiro, Brazil, 2015)."},{"key":"e_1_3_4_10_2","doi-asserted-by":"crossref","unstructured":"Y. Achdou J. Han J.-M. Lasry P.-L. Lions B. Moll Income and wealth distribution in macroeconomics: A continuous-time approach (Working pap. 23732 National Bureau of Economic Research 2017) 10.3386\/w23732.","DOI":"10.3386\/w23732"},{"key":"e_1_3_4_11_2","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/s11579-015-0157-1","article-title":"Efficiency of the price formation process in presence of high frequency participants: A mean field game analysis","volume":"10","author":"Lachapelle A.","year":"2016","unstructured":"A. Lachapelle, J.-M. Lasry, C.-A. Lehalle, P.-L. Lions, Efficiency of the price formation process in presence of high frequency participants: A mean field game analysis. Math. Financ. Econ. 10, 223\u2013262 (2016).","journal-title":"Math. Financ. Econ."},{"key":"e_1_3_4_12_2","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s11579-017-0206-z","article-title":"Mean field game of controls and an application to trade crowding","volume":"12","author":"Cardaliaguet P.","year":"2018","unstructured":"P. Cardaliaguet, C.-A. Lehalle, Mean field game of controls and an application to trade crowding. Math. Financ. Econ. 12, 335\u2013363 (2018).","journal-title":"Math. Financ. Econ."},{"key":"e_1_3_4_13_2","first-page":"1","article-title":"Algorithmic trading in competitive markets with mean field games","volume":"52","author":"Casgrain P.","year":"2019","unstructured":"P. Casgrain, S. Jaimungal, Algorithmic trading in competitive markets with mean field games. SIAM News 52, 1\u20132 (2019).","journal-title":"SIAM News"},{"key":"e_1_3_4_14_2","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/CDC.2017.8263635","volume-title":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","author":"Firoozi D.","year":"2017","unstructured":"D. Firoozi, P. E. Caines, \u201cAn optimal execution problem in finance targeting the market trading speed: An MFG formulation\u201d in 2017 IEEE 56th Annual Conference on Decision and Control (CDC) (Institute of Electrical and Electronics Engineers, 2017), pp. 7\u201314."},{"key":"e_1_3_4_15_2","doi-asserted-by":"crossref","first-page":"1572","DOI":"10.1016\/j.trb.2011.07.011","article-title":"On a mean field game approach modeling congestion and aversion in pedestrian crowds","volume":"45","author":"Lachapelle A.","year":"2011","unstructured":"A. Lachapelle, M.-T. Wolfram, On a mean field game approach modeling congestion and aversion in pedestrian crowds. Transp. Res. Part B Methodol. 45, 1572\u20131589 (2011).","journal-title":"Transp. Res. Part B Methodol."},{"key":"e_1_3_4_16_2","first-page":"1311","article-title":"Mean field games with nonlinear mobilities in pedestrian dynamics","volume":"19","author":"Burger M.","year":"2014","unstructured":"M. Burger, M. Di Francesco, P. A. Markowich, M.-T. Wolfram, Mean field games with nonlinear mobilities in pedestrian dynamics. Discrete Contin. Dyn. Syst. Ser. B 19, 1311\u20131333 (2014).","journal-title":"Discrete Contin. Dyn. Syst. Ser. B"},{"key":"e_1_3_4_17_2","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1137\/17M1119196","article-title":"Mean-field type modeling of nonlocal crowd aversion in pedestrian crowd dynamics","volume":"56","author":"Aurell A.","year":"2018","unstructured":"A. Aurell, B. Djehiche, Mean-field type modeling of nonlocal crowd aversion in pedestrian crowd dynamics. SIAM J. Contr. Optim. 56, 434\u2013455 (2018).","journal-title":"SIAM J. Contr. Optim."},{"key":"e_1_3_4_18_2","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/978-3-319-78325-3_4","volume-title":"Contributions to Partial Differential Equations and Applications","author":"Achdou Y.","year":"2019","unstructured":"Y. Achdou, J.-M. Lasry, \u201cMean field games for modeling crowd motion\u201d in Contributions to Partial Differential Equations and Applications, B. Chetverushkin , Eds. (Computational Methods in Applied Sciences, Springer, Cham, Switzerland, 2019), vol. 47, pp. 17\u201342."},{"key":"e_1_3_4_19_2","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.automatica.2018.11.029","article-title":"An integral control formulation of mean field game based large scale coordination of loads in smart grids","volume":"100","author":"Kizilkale A. C.","year":"2019","unstructured":"A. C. Kizilkale, R. Salhab, R. P. Malham\u00e9, An integral control formulation of mean field game based large scale coordination of loads in smart grids. Automatica 100, 312\u2013322 (2019).","journal-title":"Automatica"},{"key":"e_1_3_4_20_2","doi-asserted-by":"crossref","first-page":"5987","DOI":"10.1109\/TSG.2019.2895247","article-title":"A mean field game approach for distributed control of thermostatic loads acting in simultaneous energy-frequency response markets","volume":"10","author":"De Paola A.","year":"2019","unstructured":"A. De Paola, V. Trovato, D. Angeli, G. Strbac, A mean field game approach for distributed control of thermostatic loads acting in simultaneous energy-frequency response markets. IEEE Transactions Smart Grid 10, 5987\u20135999 (2019).","journal-title":"IEEE Transactions Smart Grid"},{"key":"e_1_3_4_21_2","unstructured":"D. A. Gomes J. Sa\u00fade A mean-field game approach to price formation in electricity markets. arXiv:1807.07088 (19 November 2018)."},{"key":"e_1_3_4_22_2","unstructured":"W. E J. Han Q. Li A mean-field optimal control formulation of deep learning arXiv:1807.01083 (3 July 2018)."},{"key":"e_1_3_4_23_2","doi-asserted-by":"crossref","first-page":"174905","DOI":"10.1063\/1.5081829","article-title":"Describing nonequilibrium soft matter with mean field game theory","volume":"150","author":"Welch P. M.","year":"2019","unstructured":"P. M. Welch, K. \u00d8. Rasmussen, C. F. Welch, Describing nonequilibrium soft matter with mean field game theory. J. Chem. Phys. 150, 174905 (2019).","journal-title":"J. Chem. Phys."},{"key":"e_1_3_4_24_2","volume-title":"The Master Equation and the Convergence Problem in Mean Field Games","author":"Cardaliaguet P.","year":"2019","unstructured":"P. Cardaliaguet, F. Delarue, J.-M. Lasry, P.-L. Lions, The Master Equation and the Convergence Problem in Mean Field Games (Annals of Mathematics, Princeton University Press, Princeton, NJ, 2019), vol. 201."},{"key":"e_1_3_4_25_2","doi-asserted-by":"crossref","first-page":"6573","DOI":"10.1016\/j.jde.2015.08.001","article-title":"Existence of a solution to an equation arising from the theory of mean field games","volume":"259","author":"Gangbo W.","year":"2015","unstructured":"W. Gangbo, A. \u015awi\u0119ch, Existence of a solution to an equation arising from the theory of mean field games. J. Differ. Equ. 259, 6573\u20136643 (2015).","journal-title":"J. Differ. Equ."},{"key":"e_1_3_4_26_2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-38934-9","volume-title":"Regularity Theory for Mean-Field Game Systems Regularity Theory for Mean-Field Game Systems","author":"Gomes D. A.","year":"2016","unstructured":"D. A. Gomes, E. A. Pimentel, V. Voskanyan, Regularity Theory for Mean-Field Game Systems Regularity Theory for Mean-Field Game Systems (Springer, Cham, Switzerland, 2016)."},{"key":"e_1_3_4_27_2","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/978-3-030-18921-1_5","volume-title":"Contemporary Research in Elliptic PDEs and Related Topics","author":"Cesaroni A.","year":"2019","unstructured":"A. Cesaroni, M. Cirant, \u201cIntroduction to variational methods for viscous ergodic mean-field games with local coupling\u201d in Contemporary Research in Elliptic PDEs and Related Topics, S. Dipierro, Ed. (INdAM Series, Springer, Cham, Switzerland, 2019), vol. 33, pp. 221\u2013246."},{"key":"e_1_3_4_28_2","volume-title":"Probabilistic Theory of Mean Field Games with Applications. I","author":"Carmona R.","year":"2018","unstructured":"R. Carmona, F. Delarue, Probabilistic Theory of Mean Field Games with Applications. I (Probability Theory and Stochastic Modelling, Springer, Cham, Switzerland, 2018), vol. 83."},{"key":"e_1_3_4_29_2","volume-title":"Probabilistic Theory of Mean Field Games with Applications. II","author":"Carmona R.","year":"2018","unstructured":"R. Carmona, F. Delarue, Probabilistic Theory of Mean Field Games with Applications. II (Probability Theory and Stochastic Modelling, Springer, Cham, Switzerland, 2018), vol. 84."},{"key":"e_1_3_4_30_2","volume-title":"Partial Differential Equations","author":"Evans L. C.","year":"2010","unstructured":"L. C. Evans, Partial Differential Equations (Graduate Studies in Mathematics, American Mathematical Society, Providence, RI, ed. 2, 2010), vol. 19.","edition":"2"},{"key":"e_1_3_4_31_2","volume-title":"Controlled Markov Processes and Viscosity Solutions","author":"Fleming W. H.","year":"2006","unstructured":"W. H. Fleming, H. M. Soner, Controlled Markov Processes and Viscosity Solutions (Stochastic Modelling and Applied Probability, Springer, New York, NY, ed. 2, 2006), vol. 25.","edition":"2"},{"key":"e_1_3_4_32_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-642-36433-4","volume-title":"Hamilton-Jacobi Equations: Approximations, Numerical Analysis and Applications","author":"Achdou Y.","year":"2013","unstructured":"Y. Achdou, \u201cFinite difference methods for mean field games\u201d in Hamilton-Jacobi Equations: Approximations, Numerical Analysis and Applications, P. Loreti, N. Tchou, Eds. (Lecture Notes in Mathematics, Springer, Heidelberg, Germany, 2013), vol. 74, pp. 1\u201347."},{"key":"e_1_3_4_33_2","doi-asserted-by":"crossref","first-page":"4269","DOI":"10.3934\/dcds.2015.35.4269","article-title":"A semi-Lagrangian scheme for a degenerate second order mean field game system","volume":"35","author":"Carlini E.","year":"2015","unstructured":"E. Carlini, F. J. Silva, A semi-Lagrangian scheme for a degenerate second order mean field game system. Discrete Contin. Dyn. Syst. 35, 4269\u20134292 (2015).","journal-title":"Discrete Contin. Dyn. Syst."},{"key":"e_1_3_4_34_2","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1007\/s00245-016-9391-z","article-title":"Mean field type control with congestion (II): An augmented Lagrangian method","volume":"74","author":"Achdou Y.","year":"2016","unstructured":"Y. Achdou, M. Lauri\u00e8re, Mean field type control with congestion (II): An augmented Lagrangian method. Appl. Math. Optim. 74, 535\u2013578 (2016).","journal-title":"Appl. Math. Optim."},{"key":"e_1_3_4_35_2","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1007\/s13235-016-0203-5","article-title":"Two numerical approaches to stationary mean-field games","volume":"7","author":"Almulla N.","year":"2017","unstructured":"N. Almulla, R. Ferreira, D. Gomes, Two numerical approaches to stationary mean-field games. Dyn. Games Appl. 7, 657\u2013682 (2017).","journal-title":"Dyn. Games Appl."},{"key":"e_1_3_4_36_2","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/978-3-319-49996-3_4","volume-title":"Active Particles","author":"Benamou J.-D.","year":"2017","unstructured":"J.-D. Benamou, G. Carlier, F. Santambrogio, \u201cVariational mean field games\u201d in Active Particles, N. Bellomo, P. Degond, E. Tadmor, Eds. (Advances in Theory, Models, and Applications, Modeling and Simulation in Science, Engineering and Technology, Birkh\u00e4user\/Springer, Cham, Switzerland, 2017), vol. 1, pp. 141\u2013171."},{"key":"e_1_3_4_37_2","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1142\/S0218202519500283","article-title":"An entropy minimization approach to second-order variational mean-field games","volume":"29","author":"Benamou J.-D.","year":"2019","unstructured":"J.-D. Benamou, G. Carlier, S. Di Marino, L. Nenna, An entropy minimization approach to second-order variational mean-field games. Math. Model Methods Appl. Sci. 29, 1553\u20131583 (2019).","journal-title":"Math. Model Methods Appl. Sci."},{"key":"e_1_3_4_38_2","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.na.2018.03.011","article-title":"First-order, stationary mean-field games with congestion","volume":"173","author":"Evangelista D.","year":"2018","unstructured":"D. Evangelista, R. Ferreira, D. A. Gomes, L. Nurbekyan, V. Voskanyan, First-order, stationary mean-field games with congestion. Nonlinear Anal. 173, 37\u201374 (2018).","journal-title":"Nonlinear Anal."},{"key":"e_1_3_4_39_2","unstructured":"M. Jacobs F. L\u00e9ger A fast approach to optimal transport: The back-and-forth method. arXiv:1905.12154 (29 May 2019)."},{"key":"e_1_3_4_40_2","doi-asserted-by":"crossref","first-page":"1195","DOI":"10.1007\/s10915-019-00972-9","article-title":"Algorithm for Hamilton\u2013Jacobi equations in density space via a generalized Hopf formula","volume":"80","author":"Chow Y. T.","year":"2019","unstructured":"Y. T. Chow, W. Li, S. Osher, W. Yin, Algorithm for Hamilton\u2013Jacobi equations in density space via a generalized Hopf formula. J. Sci. Comput. 80, 1195\u20131239 (2019).","journal-title":"J. Sci. Comput."},{"key":"e_1_3_4_41_2","first-page":"330","volume-title":"CEMRACS 2017\u2014Numerical Methods for Stochastic Models: Control, Uncertainty Quantification, Mean-Field","author":"Brice\u00f1o Arias L.","year":"2019","unstructured":"L. Brice\u00f1o Arias , \u201cOn the implementation of a primal-dual algorithm for second order time-dependent mean field games with local couplings\u201d in CEMRACS 2017\u2014Numerical Methods for Stochastic Models: Control, Uncertainty Quantification, Mean-Field, B. Bouchard, J.-F. Chassagneux, F. Delarue, E. Gobet, J. Lelong, Eds. (ESAIM Proceedings and Surveys, EDP Science, Les Ulis, France, 2019), vol. 65, pp. 330\u2013348."},{"key":"e_1_3_4_42_2","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1137\/18M118640X","article-title":"Solving large-scale optimization problems with a convergence rate independent of grid size","volume":"57","author":"Jacobs M.","year":"2019","unstructured":"M. Jacobs, F. L\u00e9ger, W. Li, S. Osher, Solving large-scale optimization problems with a convergence rate independent of grid size. SIAM J. Numer. Anal. 57, 1100\u20131123 (2019).","journal-title":"SIAM J. Numer. Anal."},{"key":"e_1_3_4_43_2","volume-title":"Dynamic Programming","author":"Bellman R.","year":"1957","unstructured":"R. Bellman, Dynamic Programming (Princeton University Press, Princeton, NJ, 1957)."},{"key":"e_1_3_4_44_2","doi-asserted-by":"crossref","first-page":"367","DOI":"10.4171\/PM\/2023","article-title":"Fourier approximation methods for first-order nonlocal mean-field games","volume":"75","author":"Nurbekyan L.","year":"2018","unstructured":"L. Nurbekyan, J. Sa\u00fade, Fourier approximation methods for first-order nonlocal mean-field games. Port. Math. 75, 367\u2013396 (2018).","journal-title":"Port. Math."},{"key":"e_1_3_4_45_2","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1007\/s002110050002","article-title":"A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem","volume":"84","author":"Benamou J. D.","year":"2000","unstructured":"J. D. Benamou, Y. Brenier, A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem. Numer. Math. 84, 375\u2013393 (2000).","journal-title":"Numer. Math."},{"key":"e_1_3_4_46_2","volume-title":"Optimal Transport: Old and New","author":"Villani C.","year":"2008","unstructured":"C. Villani, Optimal Transport: Old and New (Springer Science, 2008), Vol. 338."},{"key":"e_1_3_4_47_2","volume-title":"ICML\u201915: Proceedings of the 32nd International Conference on International Conference on Machine Learning,","author":"Jimenez Rezende D.","year":"2015","unstructured":"D. Jimenez Rezende, S. Mohamed, \u201cVariational inference with normalizing flows\u201d in ICML\u201915: Proceedings of the 32nd International Conference on International Conference on Machine Learning, F. Bach, D. Blei, Eds. (JMLR.org, 2015), Vol. 37."},{"key":"e_1_3_4_48_2","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1137\/141000671","article-title":"Julia: A fresh approach to numerical computing","volume":"59","author":"Bezanson J.","year":"2017","unstructured":"J. Bezanson, A. Edelman, S. Karpinski, V. B. Shah, Julia: A fresh approach to numerical computing. SIAM Rev. 59, 65\u201398 (2017).","journal-title":"SIAM Rev."},{"key":"e_1_3_4_49_2","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1007\/s40304-017-0117-6","article-title":"Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations","volume":"5","author":"E W.","year":"2017","unstructured":"W. E, J. Han, A. Jentzen, Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations. Commun. Math. Stat. 5, 349\u2013380 (2017).","journal-title":"Commun. Math. Stat."},{"key":"e_1_3_4_50_2","unstructured":"J. Han W. E Deep learning approximation for stochastic control problems. arXiv:1611.07422 (2 November 2016)."},{"key":"e_1_3_4_51_2","doi-asserted-by":"crossref","first-page":"8505","DOI":"10.1073\/pnas.1718942115","article-title":"Solving high-dimensional partial differential equations using deep learning","volume":"115","author":"Han J.","year":"2018","unstructured":"J. Han, A. Jentzen, W. E, Solving high-dimensional partial differential equations using deep learning. Proc. Natl. Acad. Sci. U.S.A. 115, 8505\u20138510 (2018).","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"e_1_3_4_52_2","doi-asserted-by":"crossref","first-page":"1339","DOI":"10.1016\/j.jcp.2018.08.029","article-title":"Dgm: A deep learning algorithm for solving partial differential equations","volume":"375","author":"Sirignano J.","year":"2018","unstructured":"J. Sirignano, K. Spiliopoulos, Dgm: A deep learning algorithm for solving partial differential equations. J. Comput. Phys. 375, 1339\u20131364 (2018).","journal-title":"J. Comput. Phys."},{"key":"e_1_3_4_53_2","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1007\/s10915-017-0529-1","article-title":"A parallel method for earth mover\u2019s distance","volume":"75","author":"Li W.","year":"2017","unstructured":"W. Li, E. K. Ryu, S. Osher, W. Yin, W. Gangbo, A parallel method for earth mover\u2019s distance. J. Sci. Comput. 75, 182\u2013197 (2017).","journal-title":"J. Sci. Comput."},{"key":"e_1_3_4_54_2","doi-asserted-by":"crossref","first-page":"97","DOI":"10.4208\/nmtma.2015.w02si","article-title":"A multilevel method for the solution of time dependent optimal transport","volume":"8","author":"Haber E.","year":"2015","unstructured":"E. Haber, R. Horesh, A multilevel method for the solution of time dependent optimal transport. Numer. Math. Theory Methods Appl. 8, 97\u2013111 (2015).","journal-title":"Numer. Math. Theory Methods Appl."},{"key":"e_1_3_4_55_2","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1561\/2200000073","article-title":"Computational optimal transport","volume":"11","author":"Gabriel P.","year":"2019","unstructured":"P. Gabriel, M. Cuturi, Computational optimal transport. Found. Trends Mach. Learn. 11, 355\u2013602 (2019).","journal-title":"Found. Trends Mach. Learn."},{"key":"e_1_3_4_56_2","unstructured":"W. Li S. Osher Constrained dynamical optimal transport and its Lagrangian formulation. arXiv:1807.00937 (11 September 2018)."},{"key":"e_1_3_4_57_2","unstructured":"L. Zhang W. E L. Wang Monge-amp\u00e8re flow for generative modeling. arXiv.org (26 September 2018)."},{"key":"e_1_3_4_58_2","unstructured":"L. Yang G. E. Karniadakis Potential flow generator with L 2 optimal transport regularity for generative models optimal transport regularity for generative models. arXiv.org (29 August 2019)."},{"key":"e_1_3_4_59_2","unstructured":"J. Lin K. Lensink E. Haber Fluid flow mass transport for generative networks. ariXiv:1910.01694 (7 October 2019)."},{"key":"e_1_3_4_60_2","unstructured":"J. Yang X. Ye R. Trivedi H. Xu H. Zha Learning deep mean field games for modeling large population behavior. arXiv:1711.03156 (22 April 2018)."},{"key":"e_1_3_4_61_2","unstructured":"R. Carmona M. Lauri\u00e8re Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games: II \u2013 The finite horizon case. arXiv:1908.01613 (5 August 2019)."},{"key":"e_1_3_4_62_2","unstructured":"R. Carmona M. Lauri\u00e8re Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games: I \u2013 The ergodic case Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games: I \u2013 The ergodic case. arXiv:1907.05980 (13 July 2019)."},{"key":"e_1_3_4_63_2","doi-asserted-by":"crossref","first-page":"B860","DOI":"10.1137\/17M1114132","article-title":"A Lagrangian gauss-Newton-Krylov solver for mass- and intensity-preserving diffeomorphic image registration","volume":"39","author":"Mang A.","year":"2017","unstructured":"A. Mang, L. Ruthotto, A Lagrangian gauss-Newton-Krylov solver for mass- and intensity-preserving diffeomorphic image registration. SIAM J. Sci. Comput. 39, B860\u2013B885 (2017).","journal-title":"SIAM J. Sci. Comput."},{"key":"e_1_3_4_64_2","volume-title":"Numerical Optimization","author":"Nocedal J.","year":"2006","unstructured":"J. Nocedal, S. Wright, Numerical Optimization (Springer Series in Operations Research and Financial Engineering, Springer Science & Business Media, New York, NY, 2006)."},{"key":"e_1_3_4_65_2","volume-title":"Introduction to Matrix Analysis","author":"Bellman R.","year":"1997","unstructured":"R. Bellman, Introduction to Matrix Analysis (Society for Industrial and Applied Mathematics, Philadelphia, PA, ed. 2, 1997).","edition":"2"},{"key":"e_1_3_4_66_2","volume-title":"Gradient Flows in Metric Spaces and in the Space of Probability Measures","author":"Ambrosio L.","year":"2008","unstructured":"L. Ambrosio, N. Gigli, G. Savar\u00e9, Gradient Flows in Metric Spaces and in the Space of Probability Measures (Lectures in Mathematics ETH Z\u00fcrich, Birkh\u00e4user Verlag, Basel, Switzerland, ed. 2, 2008).","edition":"2"},{"key":"e_1_3_4_67_2","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","article-title":"A stochastic approximation method","volume":"22","author":"Robbins H.","year":"1951","unstructured":"H. Robbins, S. Monro, A stochastic approximation method. Ann. Math. Stat. 22, 400\u2013407 (1951).","journal-title":"Ann. Math. Stat."},{"key":"e_1_3_4_68_2","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1137\/070704277","article-title":"Robust stochastic approximation approach to stochastic programming","volume":"19","author":"Nemirovski A.","year":"2009","unstructured":"A. Nemirovski, A. Juditsky, G. Lan, A. Shapiro, Robust stochastic approximation approach to stochastic programming. SIAM J. Optim. 19, 1574\u20131609 (2009).","journal-title":"SIAM J. Optim."},{"key":"e_1_3_4_69_2","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1137\/16M1080173","article-title":"Optimization methods for large-scale machine learning","volume":"60","author":"Bottou L.","year":"2018","unstructured":"L. Bottou, F. E. Curtis, J. Nocedal, Optimization methods for large-scale machine learning. SIAM Rev. 60, 223\u2013311 (2018).","journal-title":"SIAM Rev."},{"key":"e_1_3_4_70_2","unstructured":"H. Li Z. Xu G. Taylor T. Goldstein \u201cVisualizing the loss landscape of neural nets\u201d in Thirty-second Annual Conference on Neural Information Processing Systems 2018 S. Bengio Eds. https:\/\/papers.nips.cc\/paper\/7875-visualizing-the-loss-landscape-of-neural-nets.pdf. Accessed 3 April 2020."},{"key":"e_1_3_4_71_2","doi-asserted-by":"crossref","unstructured":"K. He X. Zhang S. Ren J. Sun \u201cDeep residual learning for image recognition\u201d Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition \u201c Deep residual learning for image recognition G. Hua H. J\u00e9gou Eds. (Institute of Electrical and Electronics Engineers 2016) pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_4_72_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40304-017-0103-z","article-title":"A proposal on machine learning via dynamical systems","volume":"5","author":"E W.","year":"2017","unstructured":"W. E, A proposal on machine learning via dynamical systems. Commun. Math. Stat. 5, 1\u201311 (2017).","journal-title":"Commun. Math. Stat."},{"key":"e_1_3_4_73_2","first-page":"1","article-title":"Stable architectures for deep neural networks","volume":"34","author":"Haber E.","year":"2017","unstructured":"E. Haber, L. Ruthotto, Stable architectures for deep neural networks. Inverse Probl. 34, 1\u201322 (2017).","journal-title":"Inverse Probl."},{"key":"e_1_3_4_74_2","unstructured":"Q. Li L. Chen C. Tai W. E. Maximum principle based algorithms for deep learning. arXiv:1710.09513 (2 June 2018)."},{"key":"e_1_3_4_75_2","unstructured":"B. Chang L. Meng E. Haber F. Tung D. Begert \u201cMulti-level residual networks from dynamical systems view\u201d in International Conference on Learning Representations . https:\/\/openreview.net\/pdf?id=SyJS-OgR-. Accessed 3 April 2020."},{"key":"e_1_3_4_76_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1137\/19M1247620","article-title":"Layer-parallel training of deep residual neural networks","volume":"2","author":"G\u00fcnther S.","year":"2019","unstructured":"S. G\u00fcnther, L. Ruthotto, J. B. Schroder, E. C. Cyr, N. R. Gauger, Layer-parallel training of deep residual neural networks. SIAM J. Math. Data Sci. 2, 1\u201323 (2019).","journal-title":"SIAM J. Math. Data Sci."},{"key":"e_1_3_4_77_2","doi-asserted-by":"crossref","first-page":"602","DOI":"10.21105\/joss.00602","article-title":"Flux: Elegant machine learning with Julia","volume":"3","author":"Innes M.","year":"2018","unstructured":"M. Innes, Flux: Elegant machine learning with Julia. J. Open Source Software 3, 602 (2018).","journal-title":"J. Open Source Software"},{"key":"e_1_3_4_78_2","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1007\/s10958-006-0050-9","article-title":"On a problem of Monge","volume":"133","author":"Kantorovich L. V.","year":"2006","unstructured":"L. V. Kantorovich, On a problem of Monge. J. Math. Sci. 133, 1383\u20131383 (2006).","journal-title":"J. Math. Sci."},{"key":"e_1_3_4_79_2","first-page":"65","volume-title":"Current Developments in Mathematics","author":"Evans L. C.","year":"1997","unstructured":"L. C. Evans, \u201cPartial differential equations and Monge-Kantorovich mass transfer\u201d in Current Developments in Mathematics, D. Jerison , Eds. (International Press of Boston, 1997), pp. 65\u2013126."},{"key":"e_1_3_4_80_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/b11357","volume-title":"Mathematical Aspects of Evolving Interfaces","author":"Ambrosio L.","year":"2003","unstructured":"L. Ambrosio, \u201cLecture notes on optimal transport problems\u201d in Mathematical Aspects of Evolving Interfaces, P. Colli, Ed. (Springer, Berlin, Germany, 2003), pp. 1\u201352."},{"key":"e_1_3_4_81_2","volume-title":"Topics in Optimal Transportation","author":"Villani C.","year":"2003","unstructured":"C. Villani, Topics in Optimal Transportation (American Mathematical Society, 2003)."}],"container-title":["Proceedings of the National Academy of Sciences"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.pnas.org\/syndication\/doi\/10.1073\/pnas.1922204117","content-type":"unspecified","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pnas.org\/doi\/pdf\/10.1073\/pnas.1922204117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,7]],"date-time":"2022-06-07T22:20:11Z","timestamp":1654640411000},"score":1,"resource":{"primary":{"URL":"https:\/\/pnas.org\/doi\/full\/10.1073\/pnas.1922204117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,9]]},"references-count":81,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2020,4,28]]}},"alternative-id":["10.1073\/pnas.1922204117"],"URL":"https:\/\/doi.org\/10.1073\/pnas.1922204117","relation":{},"ISSN":["0027-8424","1091-6490"],"issn-type":[{"value":"0027-8424","type":"print"},{"value":"1091-6490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,9]]},"assertion":[{"value":"2020-04-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}