Solving high-dimensional partial differential equations using deep learning
Abstract
Developing algorithms for solving high-dimensional partial differential equations (PDEs) has been an exceedingly difficult task for a long time, due to the notoriously difficult problem known as the “curse of dimensionality.” This paper introduces a deep learning-based approach that can handle general high-dimensional parabolic PDEs. To this end, the PDEs are reformulated using backward stochastic differential equations and the gradient of the unknown solution is approximated by neural networks, very much in the spirit of deep reinforcement learning with the gradient acting as the policy function. Numerical results on examples including the nonlinear Black–Scholes equation, the Hamilton–Jacobi–Bellman equation, and the Allen–Cahn equation suggest that the proposed algorithm is quite effective in high dimensions, in terms of both accuracy and cost. Furthermore, this opens up possibilities in economics, finance, operational research, and physics, by considering all participating agents, assets, resources, or particles together at the same time, instead of making ad hoc assumptions on their interrelationships.
- Authors:
-
[1];
- Princeton Univ., Princeton, NJ (United States)
- ETH Zurich, Zurich (Switzerland)
- Princeton Univ., Princeton, NJ (United States); Beijing Inst. of Big Data Research, Beijing (China)
- Publication Date:
- Research Org.:
- Princeton Univ., NJ (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC)
- OSTI Identifier:
- 1540276
- Grant/Contract Number:
- [SC0009248]
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Proceedings of the National Academy of Sciences of the United States of America
- Additional Journal Information:
- [ Journal Volume: 115; Journal Issue: 34]; Journal ID: ISSN 0027-8424
- Publisher:
- National Academy of Sciences
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; Science & Technology; Other Topics; partial differential equations; backward stochastic differential equations; high dimension; deep learning; Feynman–Kac
Citation Formats
Han, Jiequn, Jentzen, Arnulf, and E, Weinan. Solving high-dimensional partial differential equations using deep learning. United States: N. p., 2018.
Web. doi:10.1073/pnas.1718942115.
Han, Jiequn, Jentzen, Arnulf, & E, Weinan. Solving high-dimensional partial differential equations using deep learning. United States. doi:10.1073/pnas.1718942115.
Han, Jiequn, Jentzen, Arnulf, and E, Weinan. Mon .
"Solving high-dimensional partial differential equations using deep learning". United States. doi:10.1073/pnas.1718942115. https://www.osti.gov/servlets/purl/1540276.
@article{osti_1540276,
title = {Solving high-dimensional partial differential equations using deep learning},
author = {Han, Jiequn and Jentzen, Arnulf and E, Weinan},
abstractNote = {Developing algorithms for solving high-dimensional partial differential equations (PDEs) has been an exceedingly difficult task for a long time, due to the notoriously difficult problem known as the “curse of dimensionality.” This paper introduces a deep learning-based approach that can handle general high-dimensional parabolic PDEs. To this end, the PDEs are reformulated using backward stochastic differential equations and the gradient of the unknown solution is approximated by neural networks, very much in the spirit of deep reinforcement learning with the gradient acting as the policy function. Numerical results on examples including the nonlinear Black–Scholes equation, the Hamilton–Jacobi–Bellman equation, and the Allen–Cahn equation suggest that the proposed algorithm is quite effective in high dimensions, in terms of both accuracy and cost. Furthermore, this opens up possibilities in economics, finance, operational research, and physics, by considering all participating agents, assets, resources, or particles together at the same time, instead of making ad hoc assumptions on their interrelationships.},
doi = {10.1073/pnas.1718942115},
journal = {Proceedings of the National Academy of Sciences of the United States of America},
number = [34],
volume = [115],
place = {United States},
year = {2018},
month = {8}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Cited by: 7 works
Citation information provided by
Web of Science
Web of Science
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Option Pricing and Replication with Transactions Costs
journal, December 1985
- Leland, Hayne E.
- The Journal of Finance, Vol. 40, Issue 5
A numerical algorithm for a class of BSDEs via the branching process
journal, February 2014
- Henry-Labordère, Pierre; Tan, Xiaolu; Touzi, Nizar
- Stochastic Processes and their Applications, Vol. 124, Issue 2
Forward-backward stochastic differential equations and quasilinear parabolic PDEs
journal, May 1999
- Pardoux, Etienne; Tang, Shanjian
- Probability Theory and Related Fields, Vol. 114, Issue 2
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
Algorithms for overcoming the curse of dimensionality for certain Hamilton–Jacobi equations arising in control theory and elsewhere
journal, September 2016
- Darbon, Jérôme; Osher, Stanley
- Research in the Mathematical Sciences, Vol. 3, Issue 1
A Primal-Dual Algorithm for Bsdes: a Primal-Dual Algorithm for Bsdes
journal, June 2015
- Bender, Christian; Schweizer, Nikolaus; Zhuo, Jia
- Mathematical Finance, Vol. 27, Issue 3
The Pricing of Options and Corporate Liabilities
journal, May 1973
- Black, Fischer; Scholes, Myron
- Journal of Political Economy, Vol. 81, Issue 3
Recursive valuation of defaultable securities and the timing of resolution of uncertainty
journal, November 1996
- Duffie, Darrell; Schroder, Mark; Skiadas, Costis
- The Annals of Applied Probability, Vol. 6, Issue 4
Mastering the game of Go with deep neural networks and tree search
journal, January 2016
- Silver, David; Huang, Aja; Maddison, Chris J.
- Nature, Vol. 529, Issue 7587
Adaptive importance sampling in least-squares Monte Carlo algorithms for backward stochastic differential equations
journal, April 2017
- Gobet, E.; Turkedjiev, P.
- Stochastic Processes and their Applications, Vol. 127, Issue 4
Approximation theory of the MLP model in neural networks
journal, January 1999
- Pinkus, Allan
- Acta Numerica, Vol. 8
Pricing and hedging derivative securities in markets with uncertain volatilities
journal, June 1995
- Avellaneda, M.; Levy ∗, A.; ParÁS, A.
- Applied Mathematical Finance, Vol. 2, Issue 2
The randomized information complexity of elliptic PDE
journal, April 2006
- Heinrich, Stefan
- Journal of Complexity, Vol. 22, Issue 2
Option Pricing with Differential Interest Rates
journal, April 1995
- Bergman, Yaacov Z.
- Review of Financial Studies, Vol. 8, Issue 2
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
journal, November 2012
- Hinton, Geoffrey; Deng, Li; Yu, Dong
- IEEE Signal Processing Magazine, Vol. 29, Issue 6
Counterparty risk and Funding: the four Wings of the tva
journal, March 2013
- CrÉPey, StÉPhane; Gerboud, RÉMi; Grbac, Zorana
- International Journal of Theoretical and Applied Finance, Vol. 16, Issue 02
Backward Stochastic Differential Equations in Finance
journal, January 1997
- El Karoui, N.; Peng, S.; Quenez, M. C.
- Mathematical Finance, Vol. 7, Issue 1
Counterparty Risk Valuation: A Marked Branching Diffusion Approach
journal, January 2012
- Henry-Labordere, Pierre
- SSRN Electronic Journal
Implicit solution of uncertain volatility/transaction cost option pricing models with discretely observed barriers
journal, March 2001
- Forsyth, P. A.; Vetzal, K. R.
- Applied Numerical Mathematics, Vol. 36, Issue 4