arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.04778stat.MLcs.LGstat.ME
收藏

用于特征函数的生成式神经网络

Generative neural networks for characteristic functions

Florian Brück

AI总结:

本研究提出一种基于生成式神经网络的黑盒特征函数仿真算法,利用最大均值差异度量的特定表示构造损失函数,具备维度无关、无假设的通用性,并推导了有限样本近似保证,通过仿真研究验证了方法有效性。

摘要:

我们提出一种仿真算法,可从仅能以黑盒形式访问的(多变量)特征函数中生成采样。该方法基于生成式神经网络,其损失函数利用Maximum-Mean-Discrepancy(最大均值差异)度量的一种特定表示,直接纳入目标特征函数。该算法具备通用性:它不受维度限制,且无需对给定特征函数作任何假设。此外,我们还推导了以Maximum-Mean Discrepancy度量衡量的近似质量的有限样本保证。该方法的效果通过一项仿真研究得到验证。

英文摘要:

We provide a simulation algorithm to simulate from a (multivariate) characteristic function, which is only accessible in a black-box format. The method is based on 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 algorithm 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 simulation study.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑