##
**Deep backward schemes for high-dimensional nonlinear PDEs.**
*(English)*
Zbl 1440.60063

Summary: We propose new machine learning schemes for solving high-dimensional nonlinear partial differential equations (PDEs). Relying on the classical backward stochastic differential equation (BSDE) representation of PDEs, our algorithms estimate simultaneously the solution and its gradient by deep neural networks. These approximations are performed at each time step from the minimization of loss functions defined recursively by backward induction. The methodology is extended to variational inequalities arising in optimal stopping problems. We analyze the convergence of the deep learning schemes and provide error estimates in terms of the universal approximation of neural networks. Numerical results show that our algorithms give very good results till dimension 50 (and certainly above), for both PDEs and variational inequalities problems. For the PDEs resolution, our results are very similar to those obtained by the recent method in [W. E et al., Commun. Math. Stat. 5, No. 4, 349–380 (2017; Zbl 1382.65016)] when the latter converges to the right solution or does not diverge. Numerical tests indicate that the proposed methods are not stuck in poor local minima as it can be the case with the algorithm designed in the work previously mentioned, and no divergence is experienced. The only limitation seems to be due to the inability of the considered deep neural networks to represent a solution with a too complex structure in high dimension.

### MSC:

60H35 | Computational methods for stochastic equations (aspects of stochastic analysis) |

65C20 | Probabilistic models, generic numerical methods in probability and statistics |

65M12 | Stability and convergence of numerical methods for initial value and initial-boundary value problems involving PDEs |

### Keywords:

deep neural networks; nonlinear PDEs in high dimension; optimal stopping problem; backward stochastic differential equations### Citations:

Zbl 1382.65016### Software:

DGM
PDF
BibTeX
XML
Cite

\textit{C. Huré} et al., Math. Comput. 89, No. 324, 1547--1579 (2020; Zbl 1440.60063)

### References:

[1] | Avikainen, Rainer, On irregular functionals of SDEs and the Euler scheme, Finance Stoch., 13, 3, 381-401 (2009) · Zbl 1199.60198 |

[2] | Bally, Vlad; Pag\`es, Gilles, Error analysis of the optimal quantization algorithm for obstacle problems, Stochastic Process. Appl., 106, 1, 1-40 (2003) · Zbl 1075.60523 |

[3] | Beck, Christian; E, Weinan; Jentzen, Arnulf, Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations, J. Nonlinear Sci., 29, 4, 1563-1619 (2019) · Zbl 1442.91116 |

[4] | Becker, Sebastian; Cheridito, Patrick; Jentzen, Arnulf, Deep optimal stopping, J. Mach. Learn. Res., 20, Paper No. 74, 25 pp. (2019) · Zbl 1495.60029 |

[5] | Bouchard, Bruno; Chassagneux, Jean-Fran\c{c}ois, Discrete-time approximation for continuously and discretely reflected BSDEs, Stochastic Process. Appl., 118, 12, 2269-2293 (2008) · Zbl 1158.60030 |

[6] | Bouchard, Bruno; Touzi, Nizar, Discrete-time approximation and Monte-Carlo simulation of backward stochastic differential equations, Stochastic Process. Appl., 111, 2, 175-206 (2004) · Zbl 1071.60059 |

[7] | Bouchard, Bruno; Warin, Xavier, Monte-Carlo valuation of American options: facts and new algorithms to improve existing methods. Numerical methods in finance, Springer Proc. Math. 12, 215-255 (2012), Springer, Heidelberg · Zbl 1247.91196 |

[8] | Chan-Wai-Nam, Quentin; Mikael, Joseph; Warin, Xavier, Machine learning for semi linear PDEs, J. Sci. Comput., 79, 3, 1667-1712 (2019) · Zbl 1433.68332 |

[9] | E, Weinan; Han, Jiequn; Jentzen, Arnulf, Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations, Commun. Math. Stat., 5, 4, 349-380 (2017) · Zbl 1382.65016 |

[10] | E, Weinan; Hutzenthaler, Martin; Jentzen, Arnulf; Kruse, Thomas, On multilevel Picard numerical approximations for high-dimensional nonlinear parabolic partial differential equations and high-dimensional nonlinear backward stochastic differential equations, J. Sci. Comput., 79, 3, 1534-1571 (2019) · Zbl 1418.65149 |

[11] | El Karoui, N.; Kapoudjian, C.; Pardoux, E.; Peng, S.; Quenez, M. C., Reflected solutions of backward SDE’s, and related obstacle problems for PDE’s, Ann. Probab., 25, 2, 702-737 (1997) · Zbl 0899.60047 |

[12] | Gobet, Emmanuel; Lemor, Jean-Philippe; Warin, Xavier, A regression-based Monte Carlo method to solve backward stochastic differential equations, Ann. Appl. Probab., 15, 3, 2172-2202 (2005) · Zbl 1083.60047 |

[13] | Han, J.; Jentzen, A.; EW., Solving high-dimensional partial differential equations using deep learning, Proceedings of the National Academy of Sciences, 115, 34, 8505-8510 (2018) · Zbl 1416.35137 |

[14] | Han, J.; Long, J., Convergence of the deep bsde method for coupled fbsdes · Zbl 1454.60105 |

[15] | Henry-Labord\`ere, Pierre; Oudjane, Nadia; Tan, Xiaolu; Touzi, Nizar; Warin, Xavier, Branching diffusion representation of semilinear PDEs and Monte Carlo approximation, Ann. Inst. Henri Poincar\'{e} Probab. Stat., 55, 1, 184-210 (2019) · Zbl 1467.60067 |

[16] | Hornik, K.; Stinchcombe, M.; White, H., Multilayer feedforward networks are universal approximators, Neural Networks, 2, 5, 359-366 (1989) · Zbl 1383.92015 |

[17] | White, Halbert, Artificial neural networks, x+329 pp. (1992), Blackwell Publishers, Oxford · Zbl 0765.62034 |

[18] | Hutzenthaler, M.; Jentzen, A.; Kruse, T.; Nguyen, T. A., A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations · Zbl 1455.65200 |

[19] | Hutzenthaler, M.; Jentzen, A.; Kruse, T.; Nguyen, T. A.; von Wurstemberger, P., Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations, arXiv preprint arXiv:1807.01212 (2018) |

[20] | Jaillet, Patrick; Lamberton, Damien; Lapeyre, Bernard, Variational inequalities and the pricing of American options, Acta Appl. Math., 21, 3, 263-289 (1990) · Zbl 0714.90004 |

[21] | Lemor, Jean-Philippe; Gobet, Emmanuel; Warin, Xavier, Rate of convergence of an empirical regression method for solving generalized backward stochastic differential equations, Bernoulli, 12, 5, 889-916 (2006) · Zbl 1136.60351 |

[22] | Pardoux, \'{E}.; Peng, S. G., Adapted solution of a backward stochastic differential equation, Systems Control Lett., 14, 1, 55-61 (1990) · Zbl 0692.93064 |

[23] | Sirignano, Justin; Spiliopoulos, Konstantinos, DGM: a deep learning algorithm for solving partial differential equations, J. Comput. Phys., 375, 1339-1364 (2018) · Zbl 1416.65394 |

[24] | Warin, Xavier, Nesting Monte Carlo for high-dimensional non-linear PDEs, Monte Carlo Methods Appl., 24, 4, 225-247 (2018) · Zbl 07008421 |

[25] | Warin, Xavier, Nesting Monte Carlo for high-dimensional non-linear PDEs, Monte Carlo Methods Appl., 24, 4, 225-247 (2018) · Zbl 07008421 |

[26] | Zhang, Jianfeng, A numerical scheme for BSDEs, Ann. Appl. Probab., 14, 1, 459-488 (2004) · Zbl 1056.60067 |

This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.