SDE approximations of GANs training and its long-run behavior
It provides a foundational theoretical framework for understanding GAN training dynamics and stability, which is incremental but addresses a known bottleneck in GAN analysis.
This paper tackles the theoretical analysis of GAN training by approximating it with stochastic differential equations (SDEs), establishing error bounds and describing long-run behavior through invariant measures.
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.