IDEAS home Printed from https://ideas.repec.org/a/eee/spapps/v164y2023icp242-287.html
   My bibliography  Save this article

A class of dimension-free metrics for the convergence of empirical measures

Author

Listed:
  • Han, Jiequn
  • Hu, Ruimeng
  • Long, Jihao

Abstract

This paper concerns the convergence of empirical measures in high dimensions. We propose a new class of probability metrics and show that under such metrics, the convergence is free of the curse of dimensionality (CoD). Such a feature is critical for high-dimensional analysis and stands in contrast to classical metrics (e.g., the Wasserstein metric). The proposed metrics fall into the category of integral probability metrics, for which we specify criteria of test function spaces to guarantee the property of being free of CoD. Examples of the selected test function spaces include the reproducing kernel Hilbert spaces, Barron space, and flow-induced function spaces. Three applications of the proposed metrics are presented: 1. The convergence of empirical measure in the case of random variables; 2. The convergence of n-particle system to the solution to McKean–Vlasov stochastic differential equation; 3. The construction of an ɛ-Nash equilibrium for a homogeneous n-player game by its mean-field limit. As a byproduct, we prove that, given a distribution close to the target distribution measured by our metric and a certain representation of the target distribution, we can generate a distribution close to the target one in terms of the Wasserstein metric and relative entropy. Overall, we show that the proposed class of metrics is a powerful tool to analyze the convergence of empirical measures in high dimensions without CoD.

Suggested Citation

  • Han, Jiequn & Hu, Ruimeng & Long, Jihao, 2023. "A class of dimension-free metrics for the convergence of empirical measures," Stochastic Processes and their Applications, Elsevier, vol. 164(C), pages 242-287.
    • Handle: RePEc:eee:spapps:v:164:y:2023:i:c:p:242-287
    DOI: 10.1016/j.spa.2023.07.009
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0304414923001448
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.spa.2023.07.009?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. Jiequn Han & Ruimeng Hu & Jihao Long, 2020. "Convergence of Deep Fictitious Play for Stochastic Differential Games," Papers 2008.05519, arXiv.org, revised Mar 2021.
    2. Jiequn Han & Ruimeng Hu, 2019. "Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games," Papers 1912.01809, arXiv.org, revised Jun 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. Jiequn Han & Yucheng Yang & Weinan E, 2021. "DeepHAM: A Global Solution Method for Heterogeneous Agent Models with Aggregate Shocks," Papers 2112.14377, arXiv.org, revised Feb 2022.
    2. Ming Min & Ruimeng Hu, 2021. "Signatured Deep Fictitious Play for Mean Field Games with Common Noise," Papers 2106.03272, arXiv.org.
    3. Sebastian Jaimungal, 2022. "Reinforcement learning and stochastic optimisation," Finance and Stochastics, Springer, vol. 26(1), pages 103-129, January.
    4. Steven Campbell & Yichao Chen & Arvind Shrivats & Sebastian Jaimungal, 2021. "Deep Learning for Principal-Agent Mean Field Games," Papers 2110.01127, arXiv.org.
    5. Robert Balkin & Hector D. Ceniceros & Ruimeng Hu, 2023. "Stochastic Delay Differential Games: Financial Modeling and Machine Learning Algorithms," Papers 2307.06450, arXiv.org.
    6. Jiequn Han & Ruimeng Hu, 2021. "Recurrent Neural Networks for Stochastic Control Problems with Delay," Papers 2101.01385, arXiv.org, revised Jun 2021.
    7. Xiangdong Liu & Yu Gu, 2023. "Study of Pricing of High-Dimensional Financial Derivatives Based on Deep Learning," Mathematics, MDPI, vol. 11(12), pages 1-16, June.

    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:eee:spapps:v:164:y:2023:i:c:p:242-287. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/505572/description#description .

    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.