论文标题
SDE gan训练及其长期行为的近似
SDE approximations of GANs training and its long-run behavior
论文作者
论文摘要
本文通过随机微分方程（SDE）分析了gan的训练过程。它首先建立了在随机梯度算法下训练gan的SDE近似，并具有精确的误差结合分析。然后，它通过在适当条件下的SDE近似值的不变度度量描述了gan训练的长期行为。这项工作为gan培训建立了理论基础，并提供了研究其演变和稳定性的分析工具。
This paper analyzes the training process of GANs via stochastic differential equations (SDEs). It first establishes SDE approximations for the training of GANs under stochastic gradient algorithms, with precise error bound analysis. It then describes the long-run behavior of GANs training via the invariant measures of its SDE approximations under proper conditions. This work builds theoretical foundation for GANs training and provides analytical tools to study its evolution and stability.
