no code implementations • 26 Oct 2021 • Amir Zadeh, Santiago Benoit, Louis-Philippe Morency
We find RVI to be a unique tool, often superior in both performance and convergence speed to previously proposed encoderless as well as amortized VI models (e. g. VAE).
no code implementations • 3 Jan 2021 • Amir Zadeh, Santiago Benoit, Louis-Philippe Morency
In this paper we present an approach for training deep generative models solely based on solving determined systems of linear equations.