105 citations · 124 across the 7 of their papers we have counts for
7 papers
Topological Obstructions and How to Avoid Them
Babak Esmaeili, Robin Walters, Heiko Zimmermann +1
Incorporating geometric inductive biases into models can aid interpretability and generalization, but encoding to a specific geometric structure can be challenging due to the impos…
Conjugate Energy-Based Models
Hao Wu, Babak Esmaeili, Michael Wick +2
In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables. The joint density of…
Nested Variational Inference
Heiko Zimmermann, Hao Wu, Babak Esmaeili +1
We develop nested variational inference (NVI), a family of methods that learn proposals for nested importance samplers by minimizing an forward or reverse KL divergence at each lev…
Rate-Regularization and Generalization in VAEs
Alican Bozkurt, Babak Esmaeili, Jean-Baptiste Tristan +3
Variational autoencoders optimize an objective that combines a reconstruction loss (the distortion) and a KL term (the rate). The rate is an upper bound on the mutual information,…
Structured Neural Topic Models for Reviews
Babak Esmaeili, Hongyi Huang, Byron C. Wallace +1
We present Variational Aspect-based Latent Topic Allocation (VALTA), a family of autoencoding topic models that learn aspect-based representations of reviews. VALTA defines a user-…
Can VAEs Generate Novel Examples?
Alican Bozkurt, Babak Esmaeili, Dana H. Brooks +2
An implicit goal in works on deep generative models is that such models should be able to generate novel examples that were not previously seen in the training data. In this paper,…
Structured Disentangled Representations
Babak Esmaeili, Hao Wu, Sarthak Jain +6
Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disen…