Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders

arXiv:2403.08941v1 Announce Type: cross
Abstract: Inference for Variational Autoencoders (VAEs) consists of learning two models: (1) a generative model, which transforms a simple distribution over a latent space into the distribution over observed data, and (2) an inference model, which approximates the posterior of the latent codes given data. The two components are learned jointly via a lower bound to the generative model's log marginal likelihood. In early phases of joint training, the inference model poorly approximates the latent code …

abstract approximation arxiv autoencoders cs.lg data distribution generative inference model-agnostic posterior simple space stat.ml type variational autoencoders