105 citations · 124 across the 7 of their papers we have counts for
4 papers · 1 filter
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…
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,…
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,…