IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2602.05898.html

Universal approximation with signatures of non-geometric rough paths

Author

Listed:
  • Mihriban Ceylan
  • Anna P. Kwossek
  • David J. Promel

Abstract

We establish a universal approximation theorem for signatures of rough paths that are not necessarily weakly geometric. By extending the path with time and its rough path bracket terms, we prove that linear functionals of the signature of the resulting rough paths approximate continuous functionals on rough path spaces uniformly on compact sets. Moreover, we construct the signature of a path extended by its pathwise quadratic variation terms based on general pathwise stochastic integration \`a la F\"ollmer, in particular, allowing for pathwise It\^o, Stratonovich, and backward It\^o integration. In a probabilistic setting, we obtain a universal approximation result for linear functionals of the signature of continuous semimartingales extended by the quadratic variation terms, defined via stochastic It\^o integration. Numerical examples illustrate the use of signatures when the path is extended by time and quadratic variation in the context of model calibration and option pricing in mathematical finance.

Suggested Citation

  • Mihriban Ceylan & Anna P. Kwossek & David J. Promel, 2026. "Universal approximation with signatures of non-geometric rough paths," Papers 2602.05898, arXiv.org.
    • Handle: RePEc:arx:papers:2602.05898
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2602.05898
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Kei Kobayashi, 2011. "Stochastic Calculus for a Time-Changed Semimartingale and the Associated Stochastic Differential Equations," Journal of Theoretical Probability, Springer, vol. 24(3), pages 789-820, September.
    2. Federico M. Bandi & Roberto Ren`o & Sara Svaluto-Ferro, 2025. "Local signature-based expansions," Papers 2504.06351, arXiv.org.
    3. Ilya Chevyrev & Andrey Kormilitzin, 2026. "A Primer on the Signature Method in Machine Learning," Springer Finance, in: Christian Bayer & Goncalo dos Reis & Blanka Horvath & Harald Oberhauser (ed.), Signature Methods in Finance, pages 3-64, Springer.
    4. Christian Bayer & Luca Pelizzari & John Schoenmakers, 2025. "Primal and dual optimal stopping with signatures," Finance and Stochastics, Springer, vol. 29(4), pages 981-1014, October.
    5. Christian Bayer & Luca Pelizzari & John Schoenmakers, 2023. "Primal and dual optimal stopping with signatures," Papers 2312.03444, arXiv.org, revised Feb 2025.
    6. Munawar Ali & Qi Feng, 2025. "Branched Signature Model," Papers 2511.00018, arXiv.org.
    7. Erdinc Akyildirim & Matteo Gambara & Josef Teichmann & Syang Zhou, 2022. "Applications of Signature Methods to Market Anomaly Detection," Papers 2201.02441, arXiv.org, revised Feb 2022.
    8. Nicolas Perkowski & David J. Promel, 2013. "Pathwise stochastic integrals for model free finance," Papers 1311.6187, arXiv.org, revised Jun 2016.
    9. Terry Lyons & Sina Nejad & Imanol Perez Arribas, 2019. "Numerical Method for Model-free Pricing of Exotic Derivatives in Discrete Time Using Rough Path Signatures," Applied Mathematical Finance, Taylor & Francis Journals, vol. 26(6), pages 583-597, November.
    10. Christa Cuchiero & Guido Gazzani & Janka Möller & Sara Svaluto‐Ferro, 2025. "Joint calibration to SPX and VIX options with signature‐based models," Mathematical Finance, Wiley Blackwell, vol. 35(1), pages 161-213, January.
    11. Andrew L. Allan & Christa Cuchiero & Chong Liu & David J. Prömel, 2023. "Model‐free portfolio theory: A rough path approach," Mathematical Finance, Wiley Blackwell, vol. 33(3), pages 709-765, July.
    12. Christa Cuchiero & Francesca Primavera & Sara Svaluto-Ferro, 2025. "Universal approximation theorems for continuous functions of càdlàg paths and Lévy-type signature models," Finance and Stochastics, Springer, vol. 29(2), pages 289-342, April.
    13. Andrew L. Allan & Chong Liu & David J. Prömel, 2024. "A càdlàg rough path foundation for robust finance," Finance and Stochastics, Springer, vol. 28(1), pages 215-257, January.
    14. Xin Guo & Binnan Wang & Ruixun Zhang & Chaoyi Zhao, 2025. "On Consistency of Signature Using Lasso," Operations Research, INFORMS, vol. 73(5), pages 2530-2549, September.
    15. Eduardo Abi Jaber & Nathan De Carvalho, 2023. "Reconciling rough volatility with jumps," Papers 2303.07222, arXiv.org, revised Sep 2024.
    16. Andrew L. Allan & Anna P. Kwossek & Chong Liu & David J. Promel, 2025. "Pathwise analysis of log-optimal portfolios," Papers 2507.18232, arXiv.org.
    17. Eduardo Abi Jaber & Nathan de Carvalho, 2024. "Reconciling rough volatility with jumps," Post-Print hal-04295416, HAL.
    18. Owen Futter & Blanka Horvath & Magnus Wiese, 2023. "Signature Trading: A Path-Dependent Extension of the Mean-Variance Framework with Exogenous Signals," Papers 2308.15135, arXiv.org, revised Aug 2023.
    19. Imanol Perez Arribas, 2018. "Derivatives pricing using signature payoffs," Papers 1809.09466, arXiv.org.
    20. Heston, Steven L, 1993. "A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options," The Review of Financial Studies, Society for Financial Studies, vol. 6(2), pages 327-343.
    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. Mihriban Ceylan & David J. Promel, 2026. "Global universality via discrete-time signatures," Papers 2603.09773, arXiv.org.
    2. Mihriban Ceylan & David J. Promel, 2025. "Global universal approximation with Brownian signatures," Papers 2512.16396, arXiv.org.
    3. Erdinc Akyildirim & Matteo Gambara & Josef Teichmann & Syang Zhou, 2023. "Randomized Signature Methods in Optimal Portfolio Selection," Papers 2312.16448, arXiv.org.
    4. Eduardo Abi Jaber & Elie Attal, 2025. "Simulating integrated Volterra square-root processes and Volterra Heston models via Inverse Gaussian," Papers 2504.19885, arXiv.org.
    5. Eduardo Abi Jaber, 2024. "Simulation of square-root processes made simple: applications to the Heston model," Papers 2412.11264, arXiv.org, revised Jun 2025.
    6. Andrew L. Allan & Anna P. Kwossek & Chong Liu & David J. Promel, 2025. "Pathwise analysis of log-optimal portfolios," Papers 2507.18232, arXiv.org.
    7. Christa Cuchiero & Janka Moller, 2023. "Signature Methods in Stochastic Portfolio Theory," Papers 2310.02322, arXiv.org, revised Oct 2024.
    8. Eduardo Abi Jaber, 2024. "Simulation of square-root processes made simple: applications to the Heston model," Post-Print hal-04839193, HAL.
    9. Wenyuan Li & Haoqi Lyu, 2026. "Valuation of variable annuities under the Volterra mortality and rough Heston models," Papers 2604.00472, arXiv.org, revised Apr 2026.
    10. Christa Cuchiero & Francesca Primavera & Sara Svaluto-Ferro, 2025. "Universal approximation theorems for continuous functions of càdlàg paths and Lévy-type signature models," Finance and Stochastics, Springer, vol. 29(2), pages 289-342, April.
    11. Eduardo Abi Jaber & Louis-Amand Gérard, 2025. "Hedging with memory: shallow and deep learning with signatures," Université Paris1 Panthéon-Sorbonne (Post-Print and Working Papers) hal-05197836, HAL.
    12. Eduardo Abi Jaber & Louis-Amand G'erard, 2025. "Hedging with memory: shallow and deep learning with signatures," Papers 2508.02759, arXiv.org.
    13. Christa Cuchiero & Philipp Schmocker & Josef Teichmann, 2023. "Global universal approximation of functional input maps on weighted spaces," Papers 2306.03303, arXiv.org, revised Dec 2025.
    14. Eduardo Abi Jaber & Camille Illand & Shaun Xiaoyuan Li, 2024. "Joint SPX-VIX calibration with Gaussian polynomial volatility models: deep pricing with quantization hints," Post-Print hal-03902513, HAL.
    15. Elisa Al`os & `Oscar Bur'es & Rafael de Santiago & Josep Vives, 2025. "Volatility Modeling with Rough Paths: A Signature-Based Alternative to Classical Expansions," Papers 2507.23392, arXiv.org, revised Apr 2026.
    16. Munawar Ali & Purba Das & Qi Feng & Liyao Gao & Guang Lin, 2025. "Noise estimation of SDE from a single data trajectory," Papers 2509.25484, arXiv.org, revised Jan 2026.
    17. Tomoyuki Ichiba & Qijin Shi, 2025. "Unbiased Rough Integrators and No Free Lunch in Rough-Path-Based Market Models," Papers 2509.14529, arXiv.org.
    18. Christa Cuchiero & Guido Gazzani & Sara Svaluto-Ferro, 2022. "Signature-based models: theory and calibration," Papers 2207.13136, arXiv.org.
    19. Matthieu Garcin & Louis Perot, 2025. "Asymptotic and finite-sample distributions of one- and two-sample empirical relative entropy, with application to change-point detection," Papers 2512.16411, arXiv.org.
    20. Munawar Ali & Qi Feng, 2025. "Branched Signature Model," Papers 2511.00018, 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:2602.05898. 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.