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 page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

justkolesov/wasserstein1benchmark officialmentioned in paperpytorchMITSyntology: 12 samples, 8 ran (0 instrument-failed) · 4 unverified report
iamalexkorotin/KernelNeuralOptimalTransport mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Optimal Transport (arXiv:2201.12220; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is 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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

justkolesov/wasserstein1benchmark official repository 12 samples, 8 ran (0 instrument-failed) · 4 unverified
get_borders src/utils.py ran MIT (permissive) · 607e577e46e2bdb2 · report fixture: signature x:Tensor/2/float, net:callable/0/?, half_length:float/0/float · returned tuple · level recorded 2026-09-25
grad in 23 papers src/utils.py ran MIT (permissive) · e3248168eb0e100b · report fixture: signature net:callable/0/?, X:Tensor/2/float · returned Tensor · level recorded 2026-09-25
l2normalize in 31 papers src/models.py ran fingerprinted MIT (permissive) · 17385c972432c94a · report fixture: signature v:Tensor/1/float, eps:float/0/float · returned Tensor · level recorded 2026-09-25
lipschitz_one_checker src/utils.py ran MIT (permissive) · 739a575fdd1b23a4 · report fixture: signature net:callable/0/?, points:Tensor/2/float, dim:int/0/int · returned tuple · level recorded 2026-09-25
penalty src/methods.py ran MIT (permissive) · f8c9f6f28ed2a57a · report fixture: signature critic:callable/0/?, q_samples:Tensor/2/float, p_samples:Tensor/2/float, flag_penalty:str/0/str · returned Tensor · level recorded 2026-09-25
plot_images in 5 papers src/plotters.py ran MIT (permissive) · 6d490c108b9b5483 · report fixture: signature benchmark:Benchmark/0/?, num_samples:int/0/int, path:NoneType/0/?, shape:tuple/1/int · returned tuple · level recorded 2026-09-25
process_group_size src/models.py ran MIT (permissive) · be9f19d3f8e2b635 · report fixture: signature x:Tensor/3/float, num_units:int/0/int, axis:int/0/int · returned list · level recorded 2026-09-25
vecs_to_plot src/plotters.py ran MIT (permissive) · 3113f42fdacbe1e9 · report fixture: signature x:Tensor/2/float, shape:tuple/1/int · returned ndarray · level recorded 2026-09-25
PCA_plot_q_p_samples src/plotters.py unverified MIT (permissive) · 1e670671fca5679c · report
load_resnet_G src/models.py unverified MIT (permissive) · 8bdd654cb2e2c935 · report
train_CoWGAN src/methods.py unverified MIT (permissive) · ee99cab556bc594e · report
train_WGAN src/methods.py 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