# Fisher Auto-Encoders

arXiv: https://arxiv.org/abs/2007.06120 · HTML: https://mlsanity.com/paper/2007.06120/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Semi-Implicit Variational Inference via Score Matching](https://mlsanity.com/paper/2308.10014/) (2023)
- [Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network](https://mlsanity.com/paper/2304.12770/) (2023)
- [Fast approximations of the Jeffreys divergence between univariate Gaussian mixture models via exponential polynomial densities](https://mlsanity.com/paper/2107.05901/) (2021)
- [Probabilistic Autoencoder using Fisher Information](https://mlsanity.com/paper/2110.14947/) (2021)
- [On the failure of variational score matching for VAE models](https://mlsanity.com/paper/2210.13390/) (2022)

## Abstract (arXiv)

It has been conjectured that the Fisher divergence is more robust to model uncertainty than the conventional Kullback-Leibler (KL) divergence. This motivates the design of a new class of robust generative auto-encoders (AE) referred to as Fisher auto-encoders. Our approach is to design Fisher AEs by minimizing the Fisher divergence between the intractable joint distribution of observed data and latent variables, with that of the postulated/modeled joint distribution. In contrast to KL-based variational AEs (VAEs), the Fisher AE can exactly quantify the distance between the true and the model-based posterior distributions. Qualitative and quantitative results are provided on both MNIST and celebA datasets demonstrating the competitive performance of Fisher AEs in terms of robustness compared to other AEs such as VAEs and Wasserstein AEs.