option-pricing

本文提出 BeTINH 结构化条件神经求解器，通过多方向时间-参数调制与联合残差路径提升 Heston 随机波动率 PDE 参数化族的求解精度与导数保真度，强调下游敏感度指标需导数感知的评估。

This paper introduces Neural Networks with Local Converging Inputs (NNLCI) to accelerate PDE-based option pricing, combining coarse and refined mesh solutions to reduce RMSE by 4–12x in multi-asset Black–Scholes and Heston models.