Hyperspherical Variational Auto-Encoders

@article{Davidson2018HypersphericalVA,
  title={Hyperspherical Variational Auto-Encoders},
  author={Tim R. Davidson and Luca Falorsi and Nicola De Cao and Thomas Kipf and Jakub M. Tomczak},
  journal={CoRR},
  year={2018},
  volume={abs/1804.00891}
}
The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning models. But although the default choice of a Gaussian distribution for both the prior and posterior represents a mathematically convenient distribution often leading to competitive results, we show that this parameterization fails to model data with a latent hyperspherical structure. To address this issue we propose using a von Mises-Fisher (vMF) distribution instead, leading to a hyperspherical latent… CONTINUE READING

From This Paper

Figures and tables from this paper.

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…