IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2410.14788.html
   My bibliography  Save this paper

Simultaneously Solving FBSDEs and their Associated Semilinear Elliptic PDEs with Small Neural Operators

Author

Listed:
  • Takashi Furuya
  • Anastasis Kratsios

Abstract

Forward-backwards stochastic differential equations (FBSDEs) play an important role in optimal control, game theory, economics, mathematical finance, and in reinforcement learning. Unfortunately, the available FBSDE solvers operate on \textit{individual} FBSDEs, meaning that they cannot provide a computationally feasible strategy for solving large families of FBSDEs, as these solvers must be re-run several times. \textit{Neural operators} (NOs) offer an alternative approach for \textit{simultaneously solving} large families of decoupled FBSDEs by directly approximating the solution operator mapping \textit{inputs:} terminal conditions and dynamics of the backwards process to \textit{outputs:} solutions to the associated FBSDE. Though universal approximation theorems (UATs) guarantee the existence of such NOs, these NOs are unrealistically large. Upon making only a few simple theoretically-guided tweaks to the standard convolutional NO build, we confirm that ``small'' NOs can uniformly approximate the solution operator to structured families of FBSDEs with random terminal time, uniformly on suitable compact sets determined by Sobolev norms using a logarithmic depth, a constant width, and a polynomial rank in the reciprocal approximation error. This result is rooted in our second result, and main contribution to the NOs for PDE literature, showing that our convolutional NOs of similar depth and width but grow only \textit{quadratically} (at a dimension-free rate) when uniformly approximating the solution operator of the associated class of semilinear Elliptic PDEs to these families of FBSDEs. A key insight into how NOs work we uncover is that the convolutional layers of our NO can approximately implement the fixed point iteration used to prove the existence of a unique solution to these semilinear Elliptic PDEs.

Suggested Citation

  • Takashi Furuya & Anastasis Kratsios, 2024. "Simultaneously Solving FBSDEs and their Associated Semilinear Elliptic PDEs with Small Neural Operators," Papers 2410.14788, arXiv.org, revised May 2025.
  • Handle: RePEc:arx:papers:2410.14788
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2410.14788
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Jakša Cvitanić & Dylan Possamaï & Nizar Touzi, 2018. "Dynamic programming approach to principal–agent problems," Finance and Stochastics, Springer, vol. 22(1), pages 1-37, January.
    2. Akihiko Takahashi & Yoshifumi Tsuchida & Toshihiro Yamada, 2021. "A new efficient approximation scheme for solving high-dimensional semilinear PDEs: control variate method for Deep BSDE solver," CARF F-Series CARF-F-504, Center for Advanced Research in Finance, Faculty of Economics, The University of Tokyo, revised Jan 2022.
    3. Yajie Yu & Narayan Ganesan & Bernhard Hientzsch, 2023. "Backward Deep BSDE Methods and Applications to Nonlinear Problems," Risks, MDPI, vol. 11(3), pages 1-16, March.
    4. Jakša Cvitanić & Dylan Possamaï & Nizar Touzi, 2017. "Moral Hazard in Dynamic Risk Management," Management Science, INFORMS, vol. 63(10), pages 3328-3346, October.
    5. Polynice Oyono Ngou & Cody Hyndman, 2022. "A Fourier Interpolation Method for Numerical Solution of FBSDEs: Global Convergence, Stability, and Higher Order Discretizations," JRFM, MDPI, vol. 15(9), pages 1-32, August.
    6. Romuald Elie & Thibaut Mastrolia & Dylan Possamaï, 2019. "A Tale of a Principal and Many, Many Agents," Mathematics of Operations Research, INFORMS, vol. 44(2), pages 440-467, May.
    7. Masaaki Fujii & Seisho Sato & Akihiko Takahashi, 2015. "An FBSDE Approach to American Option Pricing with an Interacting Particle Method," Asia-Pacific Financial Markets, Springer;Japanese Association of Financial Economics and Engineering, vol. 22(3), pages 239-260, September.
    8. Antonis Papapantoleon & Dylan Possamai & Alexandros Saplaouras, 2016. "Existence and uniqueness results for BSDEs with jumps: the whole nine yards," Papers 1607.04214, arXiv.org, revised Nov 2018.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Camilo Hernández & Dylan Possamaï, 2024. "Time‐inconsistent contract theory," Mathematical Finance, Wiley Blackwell, vol. 34(3), pages 1022-1085, July.
    2. Dena Firoozi & Arvind V Shrivats & Sebastian Jaimungal, 2021. "Principal agent mean field games in REC markets," Papers 2112.11963, arXiv.org, revised Jun 2022.
    3. Camilo Hern'andez & Dylan Possamai, 2023. "Time-inconsistent contract theory," Papers 2303.01601, arXiv.org.
    4. Emma Hubert & Thibaut Mastrolia & Dylan Possamai & Xavier Warin, 2020. "Incentives, lockdown, and testing: from Thucydides's analysis to the COVID-19 pandemic," Papers 2009.00484, arXiv.org, revised Apr 2022.
    5. Alberto Gennaro & Thibaut Mastrolia, 2024. "Delegated portfolio management with random default," Papers 2410.13103, arXiv.org.
    6. Dylan Possamai & Nizar Touzi, 2020. "Is there a Golden Parachute in Sannikov's principal-agent problem?," Papers 2007.05529, arXiv.org, revised Oct 2022.
    7. Daniel Krv{s}ek & Dylan Possamai, 2023. "Randomisation with moral hazard: a path to existence of optimal contracts," Papers 2311.13278, arXiv.org.
    8. Beatrice Acciaio & Robert A. Crowell & Jakša Cvitanić, 2025. "A note on persistent private information," Mathematics and Financial Economics, Springer, volume 19, number 5, September.
    9. Romuald Élie & Emma Hubert & Thibaut Mastrolia & Dylan Possamaï, 2021. "Mean–field moral hazard for optimal energy demand response management," Mathematical Finance, Wiley Blackwell, vol. 31(1), pages 399-473, January.
    10. Camilo Hern'andez & Dylan Possamai, 2020. "Me, myself and I: a general theory of non-Markovian time-inconsistent stochastic control for sophisticated agents," Papers 2002.12572, arXiv.org, revised Jul 2021.
    11. Steven Campbell & Yichao Chen & Arvind Shrivats & Sebastian Jaimungal, 2021. "Deep Learning for Principal-Agent Mean Field Games," Papers 2110.01127, arXiv.org.
    12. Sarah Bensalem & Nicolás Hernández-Santibáñez & Nabil Kazi-Tani, 2023. "A continuous-time model of self-protection," Finance and Stochastics, Springer, vol. 27(2), pages 503-537, April.
    13. Guillermo Alonso Alvarez & Erhan Bayraktar & Ibrahim Ekren & Liwei Huang, 2024. "Sequential optimal contracting in continuous time," Papers 2411.04262, arXiv.org.
    14. Bastien Baldacci & Dylan Possamaï, 2022. "Governmental incentives for green bonds investment," Mathematics and Financial Economics, Springer, volume 16, number 5, September.
    15. Emma Hubert, 2023. "Continuous-time incentives in hierarchies," Finance and Stochastics, Springer, vol. 27(3), pages 605-661, July.
    16. Sarah Bensalem & Nicolás Hernández Santibáñez & Nabil Kazi-Tani, 2022. "A Continuous-Time Model of Self-Protection," Working Papers hal-02974961, HAL.
    17. Thibaut Mastrolia & Jiacheng Zhang, 2025. "Agency Problem and Mean Field System of Agents with Moral Hazard, Synergistic Effects and Accidents," Journal of Optimization Theory and Applications, Springer, vol. 205(3), pages 1-32, June.
    18. Nicolás Hernández Santibáñez & Dylan Possamaï & Chao Zhou, 2020. "Bank Monitoring Incentives Under Moral Hazard and Adverse Selection," Journal of Optimization Theory and Applications, Springer, vol. 184(3), pages 988-1035, March.
    19. René Carmona, 2022. "The influence of economic research on financial mathematics: Evidence from the last 25 years," Finance and Stochastics, Springer, vol. 26(1), pages 85-101, January.
    20. Romuald Elie & Thibaut Mastrolia & Dylan Possamaï, 2019. "A Tale of a Principal and Many, Many Agents," Mathematics of Operations Research, INFORMS, vol. 44(2), pages 440-467, May.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2410.14788. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.