IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2212.12018.html
   My bibliography  Save this paper

Langevin algorithms for Markovian Neural Networks and Deep Stochastic control

Author

Listed:
  • Pierre Bras
  • Gilles Pag`es

Abstract

Stochastic Gradient Descent Langevin Dynamics (SGLD) algorithms, which add noise to the classic gradient descent, are known to improve the training of neural networks in some cases where the neural network is very deep. In this paper we study the possibilities of training acceleration for the numerical resolution of stochastic control problems through gradient descent, where the control is parametrized by a neural network. If the control is applied at many discretization times then solving the stochastic control problem reduces to minimizing the loss of a very deep neural network. We numerically show that Langevin algorithms improve the training on various stochastic control problems like hedging and resource management, and for different choices of gradient descent methods.

Suggested Citation

  • Pierre Bras & Gilles Pag`es, 2022. "Langevin algorithms for Markovian Neural Networks and Deep Stochastic control," Papers 2212.12018, arXiv.org, revised Jan 2023.
    • Handle: RePEc:arx:papers:2212.12018
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2212.12018
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Stéphane Goutte & Idris Kharroubi & Thomas Lim, 2018. "Optimal management of an oil exploitation," International Journal of Global Energy Issues, Inderscience Enterprises Ltd, vol. 41(1/2/3/4), pages 69-85.
    2. M’hamed Gaïgi & Stéphane Goutte & Idris Kharroubi & Thomas Lim, 2021. "Optimal risk management problem of natural resources: application to oil drilling," Annals of Operations Research, Springer, vol. 297(1), pages 147-166, February.
    3. Achref Bachouch & Côme Huré & Nicolas Langrené & Huyên Pham, 2022. "Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Numerical Applications," Methodology and Computing in Applied Probability, Springer, vol. 24(1), pages 143-178, March.
    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. Pierre Bras & Gilles Pagès, 2022. "Langevin algorithms for Markovian Neural Networks and Deep Stochastic control," Working Papers hal-03980632, HAL.
    2. Olivier Bokanowski & Averil Prost & Xavier Warin, 2023. "Neural networks for first order HJB equations and application to front propagation with obstacle terms," Partial Differential Equations and Applications, Springer, vol. 4(5), pages 1-36, October.
    3. M’hamed Gaïgi & Stéphane Goutte & Idris Kharroubi & Thomas Lim, 2021. "Optimal risk management problem of natural resources: application to oil drilling," Annals of Operations Research, Springer, vol. 297(1), pages 147-166, February.
    4. Yoshioka, Hidekazu & Yoshioka, Yumi, 2024. "Assessing fluctuations of long-memory environmental variables based on the robustified dynamic Orlicz risk," Chaos, Solitons & Fractals, Elsevier, vol. 180(C).
    5. Alexandre Roch, 2023. "Optimal Liquidation Through a Limit Order Book: A Neural Network and Simulation Approach," Methodology and Computing in Applied Probability, Springer, vol. 25(1), pages 1-29, March.
    6. Laurens Van Mieghem & Antonis Papapantoleon & Jonas Papazoglou-Hennig, 2023. "Machine learning for option pricing: an empirical investigation of network architectures," Papers 2307.07657, arXiv.org.

    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:2212.12018. 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.