In this work, we provide a simulation algorithm to simulate from a (multivariate) characteristic function, which is only accessible in a black-box format. We construct a generative neural network, whose loss function exploits a specific representation of the Maximum-Mean-Discrepancy metric to directly incorporate the targeted characteristic function. The construction is universal in the sense that it is independent of the dimension and that it does not require any assumptions on the given characteristic function. Furthermore, finite sample guarantees on the approximation quality in terms of the Maximum-Mean Discrepancy metric are derived. The method is illustrated in a short simulation study.

翻译：本文提出了一种模拟算法，用于从仅以黑箱形式访问的（多元）特征函数进行模拟。我们构建了一个生成神经网络，其损失函数利用最大均值差异度量的特定表示，直接融入目标特征函数。该构造具有通用性，即不依赖于维度，且无需对给定的特征函数做出任何假设。此外，我们还推导了基于最大均值差异度量的近似质量的有限样本保证。通过一项简短的模拟研究对该方法进行了说明。