MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders
ICLR, Volume abs/1901.01498, 2019.
Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. However, recent studies demonstrate that, when equipped with expressive generative distributions (aka. decoders), VAE suffers from learning un...More
PPT (Upload PPT)