IDEAS home Printed from https://ideas.repec.org/a/spr/pardea/v2y2021i4d10.1007_s42985-021-00102-x.html
   My bibliography  Save this article

Solving high-dimensional Hamilton–Jacobi–Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space

Author

Listed:
  • Nikolas Nüsken

    (Universität Potsdam)

  • Lorenz Richter

    (Freie Universität Berlin
    Brandenburgische Technische Universität Cottbus-Senftenberg)

Abstract

Optimal control of diffusion processes is intimately connected to the problem of solving certain Hamilton–Jacobi–Bellman equations. Building on recent machine learning inspired approaches towards high-dimensional PDEs, we investigate the potential of iterative diffusion optimisation techniques, in particular considering applications in importance sampling and rare event simulation, and focusing on problems without diffusion control, with linearly controlled drift and running costs that depend quadratically on the control. More generally, our methods apply to nonlinear parabolic PDEs with a certain shift invariance. The choice of an appropriate loss function being a central element in the algorithmic design, we develop a principled framework based on divergences between path measures, encompassing various existing methods. Motivated by connections to forward-backward SDEs, we propose and study the novel log-variance divergence, showing favourable properties of corresponding Monte Carlo estimators. The promise of the developed approach is exemplified by a range of high-dimensional and metastable numerical examples.

Suggested Citation

  • Nikolas Nüsken & Lorenz Richter, 2021. "Solving high-dimensional Hamilton–Jacobi–Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space," Partial Differential Equations and Applications, Springer, vol. 2(4), pages 1-48, August.
    • Handle: RePEc:spr:pardea:v:2:y:2021:i:4:d:10.1007_s42985-021-00102-x
    DOI: 10.1007/s42985-021-00102-x
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s42985-021-00102-x
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.
    File URL: https://libkey.io/10.1007/s42985-021-00102-x?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Philipp Grohs & Fabian Hornung & Arnulf Jentzen & Philippe von Wurstemberger, 2018. "A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations," Papers 1809.02362, arXiv.org, revised Jan 2023.
    2. David M. Blei & Alp Kucukelbir & Jon D. McAuliffe, 2017. "Variational Inference: A Review for Statisticians," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 112(518), pages 859-877, April.
    3. Baudoin, Fabrice, 0. "Conditioned stochastic differential equations: theory, examples and application to finance," Stochastic Processes and their Applications, Elsevier, vol. 100(1-2), pages 109-145, July.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Becker, Simon & Hartmann, Carsten & Redmann, Martin & Richter, Lorenz, 2022. "Error bounds for model reduction of feedback-controlled linear stochastic dynamics on Hilbert spaces," Stochastic Processes and their Applications, Elsevier, vol. 149(C), pages 107-141.

    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. Shen Liu & Hongyan Liu, 2021. "Tagging Items Automatically Based on Both Content Information and Browsing Behaviors," INFORMS Journal on Computing, INFORMS, vol. 33(3), pages 882-897, July.
    2. Liu, Jie & Ye, Zifeng & Chen, Kun & Zhang, Panpan, 2024. "Variational Bayesian inference for bipartite mixed-membership stochastic block model with applications to collaborative filtering," Computational Statistics & Data Analysis, Elsevier, vol. 189(C).
    3. Bernardo D'Auria & Jos'e Antonio Salmer'on, 2017. "Optimal portfolios with anticipating information on the stochastic interest rate," Papers 1711.03642, arXiv.org, revised Jul 2024.
    4. Djohan Bonnet & Tifenn Hirtzlin & Atreya Majumdar & Thomas Dalgaty & Eduardo Esmanhotto & Valentina Meli & Niccolo Castellani & Simon Martin & Jean-François Nodin & Guillaume Bourgeois & Jean-Michel P, 2023. "Bringing uncertainty quantification to the extreme-edge with memristor-based Bayesian neural networks," Nature Communications, Nature, vol. 14(1), pages 1-13, December.
    5. Seokhyun Chung & Raed Al Kontar & Zhenke Wu, 2022. "Weakly Supervised Multi-output Regression via Correlated Gaussian Processes," INFORMS Joural on Data Science, INFORMS, vol. 1(2), pages 115-137, October.
    6. Gary Koop & Dimitris Korobilis, 2023. "Bayesian Dynamic Variable Selection In High Dimensions," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 64(3), pages 1047-1074, August.
    7. Ziqi Zhang & Xinye Zhao & Mehak Bindra & Peng Qiu & Xiuwei Zhang, 2024. "scDisInFact: disentangled learning for integration and prediction of multi-batch multi-condition single-cell RNA-sequencing data," Nature Communications, Nature, vol. 15(1), pages 1-16, December.
    8. Dimitris Korobilis & Davide Pettenuzzo, 2020. "Machine Learning Econometrics: Bayesian algorithms and methods," Working Papers 2020_09, Business School - Economics, University of Glasgow.
    9. Jan Prüser & Florian Huber, 2024. "Nonlinearities in macroeconomic tail risk through the lens of big data quantile regressions," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 39(2), pages 269-291, March.
    10. Bansal, Prateek & Krueger, Rico & Graham, Daniel J., 2021. "Fast Bayesian estimation of spatial count data models," Computational Statistics & Data Analysis, Elsevier, vol. 157(C).
    11. Maximilien Germain & Huyên Pham & Xavier Warin, 2021. "Neural networks-based algorithms for stochastic control and PDEs in finance ," Post-Print hal-03115503, HAL.
    12. Korobilis, Dimitris & Koop, Gary, 2018. "Variational Bayes inference in high-dimensional time-varying parameter models," Essex Finance Centre Working Papers 22665, University of Essex, Essex Business School.
    13. Etienne Côme & Nicolas Jouvin & Pierre Latouche & Charles Bouveyron, 2021. "Hierarchical clustering with discrete latent variable models and the integrated classification likelihood," Advances in Data Analysis and Classification, Springer;German Classification Society - Gesellschaft für Klassifikation (GfKl);Japanese Classification Society (JCS);Classification and Data Analysis Group of the Italian Statistical Society (CLADAG);International Federation of Classification Societies (IFCS), vol. 15(4), pages 957-986, December.
    14. Alex Burnap & John R. Hauser & Artem Timoshenko, 2023. "Product Aesthetic Design: A Machine Learning Augmentation," Marketing Science, INFORMS, vol. 42(6), pages 1029-1056, November.
    15. Yuan Fang & Dimitris Karlis & Sanjeena Subedi, 2022. "Infinite Mixtures of Multivariate Normal-Inverse Gaussian Distributions for Clustering of Skewed Data," Journal of Classification, Springer;The Classification Society, vol. 39(3), pages 510-552, November.
    16. Stéphane Bonhomme, 2021. "Selection on Welfare Gains: Experimental Evidence from Electricity Plan Choice," Working Papers 2021-15, Becker Friedman Institute for Research In Economics.
    17. Junming Yin & Jerry Luo & Susan A. Brown, 2021. "Learning from Crowdsourced Multi-labeling: A Variational Bayesian Approach," Information Systems Research, INFORMS, vol. 32(3), pages 752-773, September.
    18. Jeong, Kuhwan & Chae, Minwoo & Kim, Yongdai, 2023. "Online learning for the Dirichlet process mixture model via weakly conjugate approximation," Computational Statistics & Data Analysis, Elsevier, vol. 179(C).
    19. Daziano, Ricardo A., 2022. "Willingness to delay charging of electric vehicles," Research in Transportation Economics, Elsevier, vol. 94(C).
    20. Andreas Rehs, 2020. "A structural topic model approach to scientific reorientation of economics and chemistry after German reunification," Scientometrics, Springer;Akadémiai Kiadó, vol. 125(2), pages 1229-1251, November.

    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:spr:pardea:v:2:y:2021:i:4:d:10.1007_s42985-021-00102-x. 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: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    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.