# FIS-GAN: GAN with Flow-based Importance Sampling

arXiv: https://arxiv.org/abs/1910.02519 · HTML: https://mlsanity.com/paper/1910.02519/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2019.

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

- [Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction](https://mlsanity.com/paper/2112.11136/) (2021)

## Abstract (arXiv)

Generative Adversarial Networks (GAN) training process, in most cases, apply Uniform or Gaussian sampling methods in the latent space, which probably spends most of the computation on examples that can be properly handled and easy to generate. Theoretically, importance sampling speeds up stochastic optimization in supervised learning by prioritizing training examples. In this paper, we explore the possibility of adapting importance sampling into adversarial learning. We use importance sampling to replace Uniform and Gaussian sampling methods in the latent space and employ normalizing flow to approximate latent space posterior distribution by density estimation. Empirically, results on MNIST and Fashion-MNIST demonstrate that our method significantly accelerates GAN's optimization while retaining visual fidelity in generated samples.