EUVIMEDEUVIMED entdecken
Crossref

Physics-Informed Koopman Neural Estimation of the Heston Model from High-Frequency Observations

Qiuming Zhu, Haoran Kou, Linyi Qian, Chunqi Shi, Xianyi Wu, Ziwei Zhou

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (34) · 29142-29149

DOI: 10.1609/aaai.v40i34.40152 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Qiuming Zhu und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a physics-informed learning framework, called Koopman-PINN, to estimate the parameters of the Heston stochastic volatility model with high-frequency price data in financial markets. The method integrates a nonparametric volatility estimation (known as ART-filter in the literature), moment-based parameter initialization, and a neural Koopman operator constrained by the infinitesimal generator of the underlying stochastic differential equation. By incorporating a generator-based loss, the model bridges Koopman theory and neural modeling to handle partially observed coupled stochastic dynamics in a manner consistent with continuous-time evolution. Across diverse parameter combinations reflecting varying market conditions, Koopman-PINN consistently achieves accurate and robust five-parameter recovery, outperforming existing estimators under a minimal set of initialization assumptions.

Zitieren

APA

Zhu, Q., Kou, H., Qian, L., Shi, C., Wu, X., & Zhou, Z. (2026). Physics-Informed Koopman Neural Estimation of the Heston Model from High-Frequency Observations. Proceedings of the AAAI Conference on Artificial Intelligence, 40(34), 29142-29149. https://doi.org/10.1609/aaai.v40i34.40152

Vancouver

Zhu Q, Kou H, Qian L, Shi C, Wu X, Zhou Z. Physics-Informed Koopman Neural Estimation of the Heston Model from High-Frequency Observations. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(34):29142-29149. doi:10.1609/aaai.v40i34.40152

BibTeX
@article{Zhu2026,
  author = {Zhu, Qiuming and Kou, Haoran and Qian, Linyi and Shi, Chunqi and Wu, Xianyi and Zhou, Ziwei},
  title = {Physics-Informed Koopman Neural Estimation of the Heston Model from High-Frequency Observations},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {34},
  pages = {29142--29149},
  doi = {10.1609/aaai.v40i34.40152}
}
Kostenlos starten →