BriefGPT.xyz
Jan, 2020
随机微分方程的可扩展梯度
Scalable Gradients for Stochastic Differential Equations
HTML
PDF
Xuechen Li, Ting-Kam Leonard Wong, Ricky T. Q. Chen, David Duvenaud
TL;DR
本文提出一种利用伴随灵敏度方法计算随机微分方程梯度的方法，结合高阶适应性求解器，实现快速、内存高效的梯度计算。并将该方法应用于基于神经网络的随机动力学拟合中，表现出竞争性的性能。
Abstract
The
adjoint sensitivity method
scalably computes gradients of solutions to ordinary differential equations. We generalize this method to
stochastic differential equations
, allowing time-efficient and constant-mem
→