# Use of Student's t-Distribution for the Latent Layer in a Coupled Variational Autoencoder

arXiv: https://arxiv.org/abs/2011.10879 · HTML: https://mlsanity.com/paper/2011.10879/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2020.

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

- [Fat-Tailed Variational Inference with Anisotropic Tail Adaptive Flows](https://mlsanity.com/paper/2205.07918/) (2022)

## Abstract (arXiv)

A Coupled Variational Autoencoder, which incorporates both a generalized loss function and latent layer distribution, shows improvement in the accuracy and robustness of generated replicas of MNIST numerals. The latent layer uses a Student's t-distribution to incorporate heavy-tail decay. The loss function uses a coupled logarithm, which increases the penalty on images with outlier likelihood. The generalized mean of the generated image's likelihood is used to measure the performance of the algorithm's decisiveness, accuracy, and robustness.