166 citations · 218 across the 5 of their papers we have counts for
3 papers · 1 filter
Nonlocal optimization of binary neural networks
Amir Khoshaman, Giuseppe Castiglione, Christopher Srinivasa
We explore training Binary Neural Networks (BNNs) as a discrete variable inference problem over a factor graph. We study the behaviour of this conversion in an under-parameterized…
GumBolt: Extending Gumbel trick to Boltzmann priors
Amir H. Khoshaman, Mohammad H. Amin
Boltzmann machines (BMs) are appealing candidates for powerful priors in variational autoencoders (VAEs), as they are capable of capturing nontrivial and multi-modal distributions…
DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
Arash Vahdat, William G. Macready, Zhengbing Bian +2
Training of discrete latent variable models remains challenging because passing gradient information through discrete units is difficult. We propose a new class of smoothing transf…