Beyond Time Induction: Structured Conditional Neural Solvers for Parametric Stochastic-Volatility Pricing
Read the original on arXiv Machine Learning →The paper introduces BeTINN, a structured conditional neural network architecture that extends time‑induced modulation with multi‑directional time‑parameter conditioning and a joint residual pathway. BeTINN is evaluated on the Heston stochastic‑volatility PDE, showing improved accuracy for both option values and key sensitivity metrics compared to baseline models. Ablation studies highlight the contributions of each architectural component, and the authors observe that physics‑based validation loss does not fully capture derivative fidelity, underscoring the need for derivative‑aware evaluation when sensitivities are important.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.