Numerical resolution of McKean-Vlasov FBSDEs using neural networks.

We propose several algorithms to solve McKean-Vlasov Forward Backward Stochastic Differential Equations. Our schemes rely on the approximating power of neural networks to estimate the solution or its gradient through minimization problems. As a consequence, we obtain methods able to tackle both mean field games and mean field control problems in high dimension. We analyze the numerical behavior of our algorithms on several examples including non linear quadratic models.

[1]  François Delarue,et al.  Probabilistic Theory of Mean Field Games with Applications I: Mean Field FBSDEs, Control, and Games , 2018 .

[2]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[3]  Mathieu Lauriere,et al.  Numerical Methods for Mean Field Games and Mean Field Type Control , 2021, Proceedings of Symposia in Applied Mathematics.

[4]  E Weinan,et al.  Machine Learning Approximation Algorithms for High-Dimensional Fully Nonlinear Partial Differential Equations and Second-order Backward Stochastic Differential Equations , 2017, J. Nonlinear Sci..

[5]  Alexander Sergeev,et al.  Horovod: fast and easy distributed deep learning in TensorFlow , 2018, ArXiv.

[6]  D. Crisan,et al.  A Probabilistic Approach to Classical Solutions of the Master Equation for Large Population Equilibria , 2014, Memoirs of the American Mathematical Society.

[7]  Xavier Warin,et al.  Machine Learning for Semi Linear PDEs , 2018, Journal of Scientific Computing.

[8]  B. Bouchard,et al.  Discrete-time approximation and Monte-Carlo simulation of backward stochastic differential equations , 2004 .

[9]  Ying Peng,et al.  Three Algorithms for Solving High-Dimensional Fully Coupled FBSDEs Through Deep Learning , 2019, IEEE Intelligent Systems.

[10]  Jean-Pierre Fouque,et al.  Deep Learning Methods for Mean Field Control Problems With Delay , 2019, Frontiers in Applied Mathematics and Statistics.

[11]  Jiequn Han,et al.  Convergence of the deep BSDE method for coupled FBSDEs , 2018, Probability, Uncertainty and Quantitative Risk.

[12]  Mathieu Laurière,et al.  Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: I - The Ergodic Case , 2019, The Annals of Applied Probability.

[13]  Dan Crisan,et al.  CLASSICAL SOLUTIONS TO THE MASTER EQUATION FOR LARGE POPULATION EQUILIBRIA , 2014 .

[14]  P. Lions,et al.  Jeux à champ moyen. II – Horizon fini et contrôle optimal , 2006 .

[15]  P. Cardaliaguet,et al.  Mean field game of controls and an application to trade crowding , 2016, 1610.09904.

[16]  Cem Anil,et al.  Sorting out Lipschitz function approximation , 2018, ICML.

[17]  Arnulf Jentzen,et al.  Solving high-dimensional partial differential equations using deep learning , 2017, Proceedings of the National Academy of Sciences.

[18]  E. Gobet,et al.  A regression-based Monte Carlo method to solve backward stochastic differential equations , 2005, math/0508491.

[19]  Christy V. Graves,et al.  Cemracs 2017: numerical probabilistic approach to MFG , 2019, ESAIM: Proceedings and Surveys.

[20]  R. Carmona,et al.  A probabilistic weak formulation of mean field games and applications , 2013, 1307.1152.

[21]  Yves Achdou,et al.  Mean Field Games: Numerical Methods , 2010, SIAM J. Numer. Anal..

[22]  P. Lions,et al.  Jeux à champ moyen. I – Le cas stationnaire , 2006 .

[23]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[24]  Dan Crisan,et al.  Numerical method for FBSDEs of McKean–Vlasov type , 2017, The Annals of Applied Probability.

[25]  Huyên Pham,et al.  Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis , 2021, SIAM J. Numer. Anal..

[26]  Huyên Pham,et al.  Some machine learning schemes for high-dimensional nonlinear PDEs , 2019, ArXiv.

[27]  Huyên Pham,et al.  Deep backward schemes for high-dimensional nonlinear PDEs , 2019 .

[28]  René Carmona,et al.  Probabilistic Analysis of Mean-field Games , 2013 .

[29]  Huyen Pham,et al.  Neural networks-based backward scheme for fully nonlinear PDEs , 2019, SN Partial Differential Equations and Applications.

[30]  Arnulf Jentzen,et al.  Deep splitting method for parabolic PDEs , 2019, SIAM J. Sci. Comput..