Goto

Collaborating Authors

 distv ae

Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation Seunghwan An and Jong-June Jeon

Neural Information Processing Systems

The Gaussianity assumption has been consistently criticized as a main limitation of the V ariational Autoencoder (V AE) despite its efficiency in computational modeling. In this paper, we propose a new approach that expands the model capacity (i.e., expressive power of distributional family) without sacrificing the computational advantages of the V AE framework. Our V AE model's decoder is composed of an infinite mixture of asymmetric Laplace distribution, which possesses general

  Country:
  Genre: Research Report > New Finding (0.46)
  Industry:
  Technology:

Add feedback