Nonparametric Variational Auto-encoders for Hierarchical Representation Learning

Understand

The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods.

• However, most work on VAEs use a rather simple prior over the latent variables such as standard normal distribution, thereby restricting its applications to relatively simple phenomena.
• In this work, we propose hierarchical nonparametric variational autoencoders, which combines tree-structured Bayesian nonparametric priors with VAEs, to enable infinite flexibility of the latent representation space.
• Both the neural parameters and Bayesian priors are learned jointly using tailored variational inference.