Pith. sign in

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

arxiv 2103.01678 v4 pith:VY3ZOIAE submitted 2021-03-02 stat.ML cs.LG

classification stat.MLcs.LG
keywords wassersteindistancegansapproximatelosstheoreticalworkanalysis
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Distributional Determinantal Point Process for Repulsive Clustering of Distributions

    stat.ME 2026-07 conditional novelty 6.0 of 10

    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...

  2. Data-driven approaches to inverse problems

    math.NA 2025-06 unverdicted

    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.

Pith tools