Sep, 2018
证明人工神经网络克服了在数值逼近 Black-Scholes 偏微分方程中的维度灾难
A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
Philipp Grohs, Fabian Hornung, Arnulf Jentzen, Philippe von Wurstemberger
TL;DR本文揭示了人工神经网络可用于数值逼近 Black-Scholes PDEs 的实际应用,并证明了它能够在高维函数逼近中克服 “维度灾难”。