The deep parametric PDE method and applications to option pricing

The deep parametric PDE method and applications to option pricing
复制标题

深度参数偏微分方程方法及其在期权定价中的应用

DOI:
10.1016/j.amc.2022.127355
复制
发表时间:
2022
影响因子:
4
通讯作者:
Glau K
Glau K
中科院分区:
数学2区
文献类型:
--
作者:
Glau K

文献摘要

参考文献

被引文献

相似文献

我们提出、形式化并分析了深度参数 PDE 方法来求解高维参数偏微分方程,重点关注金融应用。单个神经网络在训练后无需样本解即可近似整个偏微分方程组的解。作为实际应用,我们在多元 Black-Scholes 模型中计算期权价格和希腊字母,因为迫切需要高效的方法。经过单个训练阶段后,不同时间、状态和模型参数的价格和敏感度可在毫秒内获得。利用 PDE 框架并结合无套利界限的先验知识可以显着提高性能。我们使用最多 25 个维度的示例来评估价格、希腊值和隐含波动率的准确性。与替代机器学习方法的比较证实了新方法的有效性,并揭示了基础 PDE 公式的优势。
We propose, formalise and analyse the deep parametric PDE method to solve high-dimensional parametric partial differential equations with a focus on financial applications. A single neural network approximates the solution of a whole family of PDEs after being trained without the need of sample solutions. As a practical application, we compute option prices and Greeks in the multivariate Black-Scholes model as there is an urgent need for highly efficient methods. After a single training phase, the prices and sensitivities for different times, states and model parameters are available in milliseconds. Exploiting the PDE framework and incorporating a-priori knowledge of no-arbitrage bounds improves the performance significantly. We evaluate the accuracy in the price, the Greeks and the implied volatility with examples of up to 25 dimensions. A comparison with alternative machine learning methods confirms the effectiveness of the new approach and reveals advantages of the underlying PDE formulation.
通过 Galerkin 方法进行或有债权定价的神经网络
DOI: 10.1007/978-1-4757-2644-2_9
发表时间: 1997
期刊: ArXiv
影响因子: --
作者:
E. Barucci;Umberto Cherubini;L. Landi
通讯作者: L. Landi
期权定价的基础减少
DOI: 10.2139/ssrn.1685382
发表时间: 2010
期刊: Derivatives eJournal
影响因子: --
作者:
R. Cont;Nicolas Lantos;O. Pironneau
通讯作者: O. Pironneau
半线性偏微分方程的机器学习
DOI: 10.1007/s10915-019-00908-3
发表时间: 2018
影响因子: 2.5
作者:
Quentin Chan;Joseph Mikael;X. Warin
通讯作者: X. Warin
用于估计期权价格的神经网络模型
DOI: 10.1007/bf00871937
发表时间: 1993
影响因子: 5.3
作者:
M. Malliaris;L. Salchenberger
通讯作者: L. Salchenberger
DOI: 10.1007/978-3-642-33134-3_85
发表时间: 2012
期刊: arXiv: Optimization and Control
影响因子: --
作者:
B. Haasdonk;J. Salomon;B. Wohlmuth
通讯作者: B. Wohlmuth