NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:8312
Title:Discrete Flows: Invertible Generative Models of Discrete Data


		
The authors develop autoregressive and bipartite discrete formulations of discrete flows. The reviewers felt the paper represents significant conceptual advances. However, there were some remaining concerns after the rebuttal period about the experiments. For example: "I'm perplexed as to why the authors seem resistant to running experiments on a simple binary image dataset, e.g. binarized MNIST or Caltech-101 Silhouettes. With binary data, there wouldn't be any issues with the ordinality of the pixels. And these datasets are small enough that getting results should take a matter of hours or less. This just seems like an obvious experiment to try to see how discrete flows compare with other families of generative models. It would also help to broaden the appeal of the paper to a wider audience." Please carefully account for (updated) reviewer comments in your revisions.