BriefGPT.xyz
Jun, 2023
拟合值迭代方法在双因果最优输运中的应用
Fitted Value Iteration Methods for Bicausal Optimal Transport
HTML
PDF
Erhan Bayraktar, Bingyan Han
TL;DR
本文提出了一种拟合值迭代(FVI)方法,用于计算具有适应性结构的bicausal最优传输(OT)问题,证明了样本复杂性,并展示了多层神经网络的适当结构能够满足所需的关键假设。数值实验表明,FVI在可扩展性方面优于线性规划和自适应Sinkhorn方法,同时仍保持可接受的准确性。
Abstract
We develop a
fitted value iteration
(FVI) method to compute
bicausal optimal transport
(OT) where couplings have an adapted structure. Based on the dynamic programming formulation, FVI adopts a function class to
→