REVIEW 2 cited by
Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Wasserstein GANs are based on the idea of minimising the Wasserstein distance between a real and a generated distribution. We provide an in-depth mathematical analysis of differences between the theoretical setup and the reality of training Wasserstein GANs. In this work, we gather both theoretical and empirical evidence that the WGAN loss is not a meaningful approximation of the Wasserstein distance. Moreover, we argue that the Wasserstein distance is not even a desirable loss function for deep generative models, and conclude that the success of Wasserstein GANs can in truth be attributed to a failure to approximate the Wasserstein distance.
Forward citations
Cited by 2 Pith papers
-
Distributional Determinantal Point Process for Repulsive Clustering of Distributions
A dDPP prior built on a sliced Wasserstein kernel provides a repulsive distribution-valued point process that, in a generalized Bayesian mixture model, clusters distributions into better-separated groups than a Dirich...
-
Data-driven approaches to inverse problems
A review lecture-note series that surveys classical and data-driven methods for inverse problems, focusing on adversarial regularization and provably convergent plug-and-play denoisers.
Discussion (0). Continue with ORCID to comment.