Papers › Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?

Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?

15 Jun 2022arXiv:2206.07767archive 2025-07-28

Alexander Korotin, Alexander Kolesov, Evgeny Burnaev

Wasserstein Generative Adversarial Networks (WGANs) are the popular generative models built on the theory of Optimal Transport (OT) and the Kantorovich duality. Despite the success of WGANs, it is still unclear how well the underlying OT dual solvers approximate the OT cost (Wasserstein-1 distance, 𝕎₁) and the OT gradient needed to update the generator. In this paper, we address these questions. We construct 1-Lipschitz functions and use them to build ray monotone transport plans. This strategy yields pairs of continuous benchmark distributions with the analytically known OT plan, OT cost and OT gradient in high-dimensional spaces such as spaces of images. We thoroughly evaluate popular WGAN dual form solvers (gradient penalty, spectral normalization, entropic regularization, etc.) using these benchmark pairs. Even though these solvers perform well in WGANs, none of them faithfully compute 𝕎₁ in high dimensions. Nevertheless, many provide a meaningful approximation of the OT gradient. These observations suggest that these solvers should not be treated as good estimators of 𝕎₁, but to some extent they indeed can be used in variational problems requiring the minimization of 𝕎₁.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2206.07767")

Code

Syntology Ran 8 of 12 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

justkolesov/wasserstein1benchmark officialmentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 8 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

8ran
4unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from justkolesov/Wasserstein1Benchmark. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_borders justkolesov/Wasserstein1Benchmark/src/utils.py official repository ran MIT (permissive) · 607e577e46e2bdb2 · report
grad justkolesov/Wasserstein1Benchmark/src/utils.py official repository ran MIT (permissive) · e3248168eb0e100b · report
l2normalize justkolesov/Wasserstein1Benchmark/src/models.py official repository ran fingerprinted MIT (permissive) · 17385c972432c94a · report
lipschitz_one_checker justkolesov/Wasserstein1Benchmark/src/utils.py official repository ran MIT (permissive) · 739a575fdd1b23a4 · report
penalty justkolesov/Wasserstein1Benchmark/src/methods.py official repository ran MIT (permissive) · f8c9f6f28ed2a57a · report
plot_images justkolesov/Wasserstein1Benchmark/src/plotters.py official repository ran MIT (permissive) · 6d490c108b9b5483 · report
process_group_size justkolesov/Wasserstein1Benchmark/src/models.py official repository ran MIT (permissive) · be9f19d3f8e2b635 · report
vecs_to_plot justkolesov/Wasserstein1Benchmark/src/plotters.py official repository ran MIT (permissive) · 3113f42fdacbe1e9 · report
PCA_plot_q_p_samples justkolesov/Wasserstein1Benchmark/src/plotters.py official repository unverified MIT (permissive) · 1e670671fca5679c · report
load_resnet_G justkolesov/Wasserstein1Benchmark/src/models.py official repository unverified MIT (permissive) · 8bdd654cb2e2c935 · report
train_CoWGAN justkolesov/Wasserstein1Benchmark/src/methods.py official repository unverified MIT (permissive) · ee99cab556bc594e · report
train_WGAN justkolesov/Wasserstein1Benchmark/src/methods.py official repository unverified MIT (permissive) · b7df65799c478813 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionWGAN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections