# SDE approximations of GANs training and its long-run behavior

arXiv: https://arxiv.org/abs/2006.02047 · HTML: https://mlsanity.com/paper/2006.02047/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2020.

## Built on by (most cited first, 1 of 1)

- [Convergence of GANs Training: A Game and Stochastic Control Methodology](https://mlsanity.com/paper/2112.00222/) (2021)

## Abstract (arXiv)

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.