2018

Convergence of the Deep BSDE Method for Coupled FBSDEs

Han, Jiequn, Long, Jihao

Understand

The recently proposed numerical algorithm, deep BSDE method, has shown remarkable performance in solving high-dimensional forward-backward stochastic differential equations (FBSDEs) and parabolic partial differential equations (PDEs).

This article lays a theoretical foundation for the deep BSDE method in the general case of coupled FBSDEs.
In particular, a posteriori error estimation of the solution is provided and it is proved that the error converges to zero given the universal approximation capability of neural networks.
Numerical results are presented to demonstrate the accuracy of the analyzed algorithm in solving high-dimensional coupled FBSDEs.

Built on

Dynamic Programming
Richard E. Bellman · 1957
Earlier work this paper cites.
Approximation by superpositions of a sigmoidal function
George Cybenko · 1989
Earlier work this paper cites.
On the approximate realization of continuous mappings by neural networks
Ken-Ichi Funahashi · 1989
Earlier work this paper cites.
Multilayer feedforward networks are universal approximators
Kurt Hornik, Maxwell Stinchcombe, and Halbert White · 1989
Earlier work this paper cites.
Backward stochastic differential equations and quasilinear parabolic partial differential equations
Etienne Pardoux and Shige Peng · 1992
Earlier work this paper cites.
Universal approximation bounds for superpositions of a sigmoidal function
Andrew R. Barron · 1993
Earlier work this paper cites.
Backward-forward stochastic differential equations
Fabio Antonelli · 1993
Earlier work this paper cites.
Solving forward-backward stochastic differential equations explicitly–a four step scheme
Jin Ma, Philip Protter, and Jiongmin Yong · 1994
Earlier work this paper cites.
Forward-backward stochastic differential equations and quasilinear parabolic PDEs
Etienne Pardoux and Shanjian Tang · 1999
Earlier work this paper cites.
On the Malliavin approach to Monte Carlo approximation of conditional expectations
Bruno Bouchard, Ivar Ekeland, and Nizar Touzi · 2004
Earlier work this paper cites.
Discrete-time approximation and Monte-Carlo simulation of backward stochastic differential equations
Bruno Bouchard and Nizar Touzi · 2004
Earlier work this paper cites.
A numerical scheme for BSDEs
Jianfeng Zhang · 2004
Earlier work this paper cites.
Numerical algorithms for forward-backward stochastic differential equations
G.N. Milstein and M.V. Tretyakov · 2006
Earlier work this paper cites.

Similar

Forward-Backward Stochastic Differential Equations and their Applications
Jin Ma and Jiongmin Yong · 2007
Cited alongside, same era.
Time discretization and Markovian iteration for coupled FBSDEs
Christian Bender and Jianfeng Zhang · 2008
Cited alongside, same era.
Least-squares Monte Carlo for backward SDEs
Christian Bender and Jessica Steiner · 2012
Cited alongside, same era.
Counterparty risk valuation: A marked branching diffusion approach
Pierre Henry-Labordere · 2012
Cited alongside, same era.
Batch normalization: Accelerating deep network training by reducing internal covariate shift
Sergey Ioffe and Christian Szegedy · 2015
Cited alongside, same era.
Adam: a method for stochastic optimization
Diederik Kingma and Jimmy Ba · 2015
Cited alongside, same era.
Multilevel Picard iterations for solving smooth semilinear parabolic heat equations
Original
Martin Hutzenthaler, Arnulf Jentzen, and Thomas Kruse · 2016
Cited alongside, same era.
The power of depth for feedforward neural networks
Ronen Eldan and Ohad Shamir · 2016
Cited alongside, same era.
On the expressive power of deep learning: A tensor analysis
Nadav Cohen, Or Sharir, and Amnon Shashua · 2016
Cited alongside, same era.
Deep vs. shallow networks: An approximation theory perspective
Hrushikesh N Mhaskar and Tomaso Poggio · 2016
Cited alongside, same era.
Efficient numerical Fourier methods for coupled forward–backward SDEs
T.P. Huijskens, M.J. Ruijter, and C.W. Oosterlee · 2016
Cited alongside, same era.
Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
Weinan E, Jiequn Han, and Arnulf Jentzen · 2017
Cited alongside, same era.

Then

Optimal approximation with sparsely connected deep neural networks
Original
Helmut Bölcskei, Philipp Grohs, Gitta Kutyniok, and Philipp Petersen · 2017
Later among the works it cites.
Why deep neural networks for function approximation?
Shiyu Liang and R Srikant · 2017
Later among the works it cites.
Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
Original
Martin Hutzenthaler, Arnulf Jentzen, Thomas Kruse, Tuan Anh Nguyen, and Philippe von Wurstemberger · 2018
Closest in time.
Solving high-dimensional partial differential equations using deep learning
Jiequn Han, Arnulf Jentzen, and Weinan E · 2018
Closest in time.
Understanding deep neural networks with rectified linear units
Raman Arora, Amitabh Basu, Poorya Mianjy, and Anirbit Mukherjee · 2018
Closest in time.
A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
Original
Philipp Grohs, Fabian Hornung, Arnulf Jentzen, and Philippe von Wurstemberger · 2018
Closest in time.
A proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients
Original
Arnulf Jentzen, Diyora Salimova, and Timo Welti · 2018
Closest in time.
Analysis of the generalization error: Empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
Original
Julius Berner, Philipp Grohs, and Arnulf Jentzen · 2018
Closest in time.
Branching diffusion representation of semilinear PDEs and Monte Carlo approximation
Pierre Henry-Labordere, Nadia Oudjane, Xiaolu Tan, Nizar Touzi, Xavier Warin, et al · 2019
Closest in time.
On multilevel Picard numerical approximations for high-dimensional nonlinear parabolic partial differential equations and high-dimensional nonlinear backward stochastic differential equations
Weinan E, Martin Hutzenthaler, Arnulf Jentzen, and Thomas Kruse · 2019
Closest in time.
Deep fictitious play for finding Markovian Nash equilibrium in multi-agent games
Original
Jiequn Han and Ruimeng Hu · 2019
Closest in time.
Solving high-dimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach
Original
Jiequn Han, Jianfeng Lu, and Mo Zhou · 2020
Closest in time.
A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
Martin Hutzenthaler, Arnulf Jentzen, Thomas Kruse, and Tuan Anh Nguyen · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…