IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2306.12658.html
   My bibliography  Save this paper

Fitted Value Iteration Methods for Bicausal Optimal Transport

Author

Listed:
  • Erhan Bayraktar
  • Bingyan Han

Abstract

We develop a fitted value iteration (FVI) method to compute bicausal optimal transport (OT) where couplings have an adapted structure. Based on the dynamic programming formulation, FVI adopts a function class to approximate the value functions in bicausal OT. Under the concentrability condition and approximate completeness assumption, we prove the sample complexity using (local) Rademacher complexity. Furthermore, we demonstrate that multilayer neural networks with appropriate structures satisfy the crucial assumptions required in sample complexity proofs. Numerical experiments reveal that FVI outperforms linear programming and adapted Sinkhorn methods in scalability as the time horizon increases, while still maintaining acceptable accuracy.

Suggested Citation

  • Erhan Bayraktar & Bingyan Han, 2023. "Fitted Value Iteration Methods for Bicausal Optimal Transport," Papers 2306.12658, arXiv.org, revised Nov 2023.
    • Handle: RePEc:arx:papers:2306.12658
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2306.12658
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Julio Backhoff-Veraguas & Daniel Bartl & Mathias Beiglböck & Manu Eder, 2020. "Adapted Wasserstein distances and stability in mathematical finance," Finance and Stochastics, Springer, vol. 24(3), pages 601-632, July.
    2. Alois Pichler & Michael Weinhardt, 2022. "The nested Sinkhorn divergence to learn the nested distance," Computational Management Science, Springer, vol. 19(2), pages 269-293, June.
    3. Tobias Achterberg & Robert E. Bixby & Zonghao Gu & Edward Rothberg & Dieter Weninger, 2020. "Presolve Reductions in Mixed Integer Programming," INFORMS Journal on Computing, INFORMS, vol. 32(2), pages 473-506, April.
    4. Langer, Sophie, 2021. "Approximating smooth functions by deep neural networks with sigmoid activation function," Journal of Multivariate Analysis, Elsevier, vol. 182(C).
    5. Julio Backhoff-Veraguas & Daniel Bartl & Mathias Beiglbock & Manu Eder, 2019. "Adapted Wasserstein Distances and Stability in Mathematical Finance," Papers 1901.07450, arXiv.org, revised May 2020.
    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. Park, Kyunghyun & Wong, Hoi Ying & Yan, Tingjin, 2023. "Robust retirement and life insurance with inflation risk and model ambiguity," Insurance: Mathematics and Economics, Elsevier, vol. 110(C), pages 1-30.
    2. Beatrice Acciaio & Stephan Eckstein & Songyan Hou, 2024. "Time-Causal VAE: Robust Financial Time Series Generator," Papers 2411.02947, arXiv.org.
    3. Nicolas Boursin & Carl Remlinger & Joseph Mikael & Carol Anne Hargreaves, 2022. "Deep Generators on Commodity Markets; application to Deep Hedging," Papers 2205.13942, arXiv.org.
    4. Julio Backhoff-Veraguas & Xin Zhang, 2023. "Dynamic Cournot-Nash equilibrium: the non-potential case," Mathematics and Financial Economics, Springer, volume 17, number 1, December.
    5. Beatrice Acciaio & Julio Backhoff & Gudmund Pammer, 2022. "Quantitative Fundamental Theorem of Asset Pricing," Papers 2209.15037, arXiv.org, revised Jan 2024.
    6. Michael Kupper & Max Nendel & Alessandro Sgarabottolo, 2023. "Risk measures based on weak optimal transport," Papers 2312.05973, arXiv.org.
    7. Benjamin Jourdain & Gudmund Pammer, 2023. "An extension of martingale transport and stability in robust finance," Papers 2304.09551, arXiv.org.
    8. Bingyan Han, 2022. "Distributionally robust risk evaluation with a causality constraint and structural information," Papers 2203.10571, arXiv.org, revised Aug 2024.
    9. Beatrice Acciaio & Anastasis Kratsios & Gudmund Pammer, 2022. "Designing Universal Causal Deep Learning Models: The Geometric (Hyper)Transformer," Papers 2201.13094, arXiv.org, revised Mar 2023.
    10. Nathan Sauldubois & Nizar Touzi, 2024. "First order Martingale model risk and semi-static hedging," Papers 2410.06906, arXiv.org.
    11. Beatrice Acciaio & Mathias Beiglboeck & Gudmund Pammer, 2020. "Weak Transport for Non-Convex Costs and Model-independence in a Fixed-Income Market," Papers 2011.04274, arXiv.org, revised Aug 2023.
    12. Beatrice Acciaio & Daniel Krv{s}ek & Gudmund Pammer, 2024. "Multicausal transport: barycenters and dynamic matching," Papers 2401.12748, arXiv.org.
    13. Julio Backhoff-Veraguas & Gudmund Pammer & Walter Schachermayer, 2024. "The Gradient Flow of the Bass Functional in Martingale Optimal Transport," Papers 2407.18781, arXiv.org.
    14. Nicolas Boursin & Carl Remlinger & Joseph Mikael, 2022. "Deep Generators on Commodity Markets Application to Deep Hedging," Risks, MDPI, vol. 11(1), pages 1-18, December.
    15. Mathias Beiglbock & Gudmund Pammer & Lorenz Riess, 2024. "Change of numeraire for weak martingale transport," Papers 2406.07523, arXiv.org.
    16. Erhan Bayraktar & Leonid Dolinskyi & Yan Dolinsky, 2020. "Extended weak convergence and utility maximisation with proportional transaction costs," Finance and Stochastics, Springer, vol. 24(4), pages 1013-1034, October.
    17. Beatrice Acciaio & Julio Backhoff-Veraguas & Junchao Jia, 2020. "Cournot-Nash equilibrium and optimal transport in a dynamic setting," Papers 2002.08786, arXiv.org, revised Nov 2020.
    18. John Armstrong & Andrei Ionescu, 2023. "Gamma Hedging and Rough Paths," Papers 2309.05054, arXiv.org, revised Mar 2024.
    19. Cohen, Asaf & Saha, Subhamay, 2021. "Asymptotic optimality of the generalized cμ rule under model uncertainty," Stochastic Processes and their Applications, Elsevier, vol. 136(C), pages 206-236.
    20. Ruslan Mirmominov & Johannes Wiesel, 2024. "A dynamic programming principle for multiperiod control problems with bicausal constraints," Papers 2410.23927, arXiv.org.

    More about this item

    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:2306.12658. 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.