← Search

Mehdi Rezaee

2 accepted papers

2020

A Discrete Variational Recurrent Topic Model without the Reparametrization Trick

NeurIPS 2020poster

We show how to learn a neural topic model with discrete random variables---one that explicitly models each word's assigned topic---using neural variational inference that does not rely on stochastic backpropagation to handle the discrete variables. The model we utilize combines the expressive power…