Variational auto-encoders with Student's t-prior

Najmeh Abiri; Mattias Ohlsson

Variational auto-encoders with Student's t-prior

Machine Learning 2020-04-07 v1 Machine Learning

Authors: Najmeh Abiri , Mattias Ohlsson

Abstract

We propose a new structure for the variational auto-encoders (VAEs) prior, with the weakly informative multivariate Student's t-distribution. In the proposed model all distribution parameters are trained, thereby allowing for a more robust approximation of the underlying data distribution. We used Fashion-MNIST data in two experiments to compare the proposed VAEs with the standard Gaussian priors. Both experiments showed a better reconstruction of the images with VAEs using Student's t-prior distribution.

Keywords

variational autoencoder

Cite

@article{arxiv.2004.02581,
  title  = {Variational auto-encoders with Student's t-prior},
  author = {Najmeh Abiri and Mattias Ohlsson},
  journal= {arXiv preprint arXiv:2004.02581},
  year   = {2020}
}

Related papers

View all related →

Machine Learning · Statistics

$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence