Batch norm with entropic regularization turns deterministic autoencoders into generative models
Abstract
The variational autoencoder is a well defined deep generative model that utilizes an encoder-decoder framework where an encoding neural network outputs a non-deterministic code for reconstructing an input. The encoder achieves this by sampling from a distribution for every input, instead of outputting a deterministic code per input. The great advantage of this process is that it allows the use of the network as a generative model for sampling from the data distribution beyond provided samples for training. We show in this work that utilizing batch normalization as a source for non-determinism suffices to turn deterministic autoencoders into generative models on par with variational ones, so long as we add a suitable entropic regularization to the training objective.
Cite
@article{arxiv.2002.10631,
title = {Batch norm with entropic regularization turns deterministic autoencoders into generative models},
author = {Amur Ghose and Abdullah Rashwan and Pascal Poupart},
journal= {arXiv preprint arXiv:2002.10631},
year = {2021}
}