# Comparison of Maximum Likelihood and GAN-based training of Real NVPs

arXiv: https://arxiv.org/abs/1705.05263 · HTML: https://mlsanity.com/paper/1705.05263/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2017.

## Built on by (most cited first, 2 of 2)

- [Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition](https://mlsanity.com/paper/2209.04920/) (2022)
- [Training Invertible Neural Networks as Autoencoders](https://mlsanity.com/paper/2303.11239/) (2023)

## Abstract (arXiv)

We train a generator by maximum likelihood and we also train the same generator architecture by Wasserstein GAN. We then compare the generated samples, exact log-probability densities and approximate Wasserstein distances. We show that an independent critic trained to approximate Wasserstein distance between the validation set and the generator distribution helps detect overfitting. Finally, we use ideas from the one-shot learning literature to develop a novel fast learning critic.