Preventing oversmoothing in VAE via generalized variance parameterization

VAE Learning via Stein Variational Gradient Descent

A new method for learning variational autoencoders (VAEs) is developed, based on Stein variational gradient descent. A key advantage of this approach is that one need not make parametric assumptions about the form of the encoder distribution. Performance is further enhanced by integrating the proposed encoder with importance sampling. Excellent performance is demonstrated across multiple unsupe...

Inferences on the Generalized Variance under Normality

Generalized variance is applied for determination of dispersion in a multivariate population and is a successful measure for concentration of multivariate data. In this article, we consider constructing confidence interval and testing the hypotheses about generalized variance in a multivariate normal distribution and give a computational approach. Simulation studies are performed to compare thi...

VAE with a VampPrior

Many different methods to train deep generative models have been introduced in the past. In this paper, we propose to extend the variational auto-encoder (VAE) framework with a new type of prior which we call "Variational Mixture of Posteriors" prior, or VampPrior for short. The VampPrior consists of a mixture distribution (e.g., a mixture of Gaussians) with components given by variational post...

Appendix for “VAE Learning via Stein Variational Gradient Descent”

Generalized Analysis of Molecular Variance

Many studies in the fields of genetic epidemiology and applied population genetics are predicated on, or require, an assessment of the genetic background diversity of the individuals chosen for study. A number of strategies have been developed for assessing genetic background diversity. These strategies typically focus on genotype data collected on the individuals in the study, based on a panel...