Symmetric Equilibrium Learning of VAEs

arXiv:2307.09883v2 Announce Type: replace
Abstract: We view variational autoencoders (VAE) as decoder-encoder pairs, which map distributions in the data space to distributions in the latent space and vice versa. The standard learning approach for VAEs is the maximisation of the evidence lower bound (ELBO). It is asymmetric in that it aims at learning a latent variable model while using the encoder as an auxiliary means only. Moreover, it requires a closed form a-priori latent distribution. This limits its applicability in …

abstract arxiv autoencoders cs.lg data decoder encoder equilibrium evidence map space standard type vae variational autoencoders view