Research map / Probabilistic and scientific modeling / Differential equations and PDEs
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
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use ART filter instead of RW-RV (ablation) | Koopman-PINN · Heston Case F | MSE of sigma: 0.008 -> 0.004 | Improved |
| use ART filter instead of EWMA-0.94 (ablation) | Koopman-PINN · Heston Case F | MSE of sigma: 0.011 -> 0.004 | Improved |
| use ART filter instead of EWMA-0.97 (ablation) | Koopman-PINN · Heston Case F | MSE of kappa: 0.336 -> 0.226 | Improved |
| use ART filter instead of GARCH(1,1) (ablation) | Koopman-PINN · Heston Case F | MSE of sigma: 0.025 -> 0.004 | Improved |
| use ART filter instead of GARCH(1,1) (ablation) | Koopman-PINN · Heston Case F | MSE of kappa: 0.434 -> 0.226 | Improved |
| use ART filter instead of RW-RV (ablation) | Koopman-PINN · Heston Case F | MSE of kappa: 0.259 -> 0.226 | Improved |
| use Koopman-PINN instead of GMM | GMM · Heston Case A (kappa,theta,sigma) | MSE of kappa: 33.4 -> 0.234 | Improved |
| use Koopman-PINN instead of QMLE | QMLE · Heston Case A (kappa,theta,sigma) | MSE of sigma: 2.78 -> 0.002 | Improved |
| use Koopman-PINN instead of EMLE | EMLE · Heston Case F (kappa,theta,sigma) | MSE of kappa: 63.6 -> 0.226 | Improved |
| use Koopman-PINN instead of Joint-Lik | Joint-Lik · Heston Case A full 5 parameters | MSE of kappa: 81.0 -> 0.233 | Improved |
| use Koopman-PINN instead of EKF-ML | EKF-ML · Heston Case A full 5 parameters | MSE of kappa: 0.223 -> 0.233 | Hurt |
| use Koopman-PINN instead of EKF-ML | EKF-ML · Heston Case A full 5 parameters | MSE of sigma: 0.583 -> 0.002 | Improved |
Closest papers by meaning
- In-Context Learning of Stochastic Differential Equations with Foundation Inference Models (NeurIPS 2025 · similarity 0.85)
- KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series Analysis (ICML 2025 · similarity 0.85)
- HyperIV: Real-time Implied Volatility Smoothing (ICML 2025 · similarity 0.85)
- Operator Deep Smoothing for Implied Volatility (ICLR 2025 · similarity 0.85)
- From GARCH to Neural Network for Volatility Forecast (AAAI 2024 · similarity 0.84)
- Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
