Learning Hierarchical Priors in VAEs – argmax.ai

Learning Hierarchical Priors in VAEs – argmax.ai

Learning Hierarchical Priors in VAEs – argmax.ai

We address the issue of learning informative latent representations of data. In the normal VAE, the latent space prior is a standard normal distribution. This over-regularises the posterior distribution, resulting in latent representations that do not represent well the structure of the data. This post, describing our 2019 NeurIPS publication, proposes and demonstrates a solution by using an hierarchical latent space prior.

Source: argmax.ai/blog/vhp-vae/