Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias. (arXiv:2112.06868v2 [cs.LG] UPDATED)

Variational Autoencoders are one of the most commonly used generative models,
particularly for image data. A prominent difficulty in training VAEs is data
that is supported on a lower-dimensional manifold. Recent work by Dai and Wipf
(2020) proposes a two-stage training algorithm for VAEs, based on a conjecture
that in standard VAE training the generator will converge to a solution with 0
variance which is correctly supported on the ground truth manifold. They gave
partial support for that conjecture by …

arxiv bias data landscape variational autoencoders