In this paper, we propose conjugate energy-based models (CEBMs), a new c...
We develop nested variational inference (NVI), a family of methods that ...
We evaluate the ability of variational autoencoders to generalize to uns...
An implicit goal in works on deep generative models is that such models
...
We present Variational Aspect-based Latent Topic Allocation (VALTA), a f...
We present Variational Aspect-Based Latent Dirichlet Allocation (VALDA),...
Deep latent-variable models learn representations of high-dimensional da...