Papers › Universal Neural Optimal Transport

Universal Neural Optimal Transport

30 Nov 2022arXiv:2212.00133archive 2025-07-28

Jonathan Geuter, Gregor Kornhardt, Ingimar Tomasson, Vaios Laschos

Optimal Transport (OT) problems are a cornerstone of many applications, but solving them is computationally expensive. To address this problem, we propose UNOT (Universal Neural Optimal Transport), a novel framework capable of accurately predicting (entropic) OT distances and plans between discrete measures for a given cost function. UNOT builds on Fourier Neural Operators, a universal class of neural networks that map between function spaces and that are discretization-invariant, which enables our network to process measures of variable resolutions. The network is trained adversarially using a second, generating network and a self-supervised bootstrapping loss. We ground UNOT in an extensive theoretical framework. Through experiments on Euclidean and non-Euclidean domains, we show that our network not only accurately predicts OT distances and plans across a wide range of datasets, but also captures the geometry of the Wasserstein space correctly. Furthermore, we show that our network can be used as a state-of-the-art initialization for the Sinkhorn algorithm with speedups of up to 7.4×, significantly outperforming existing approaches.

PaperPDFCodeCode Syntology ran

In Syntology 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="2212.00133")

Code

Syntology Ran 8 of 13 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong; 2 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 5 ran; found in paper text by Syntology: 5 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

j-geuter/sinkhornnnhybrid officialmentioned in papermentioned on GitHub 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

13 samples harvested; 8 ran; 2 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
2ran · fixture could not drive it
2ran
5unverified

Licence: 8 of the 13 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

FCNN j-geuter/sinkhornnnhybrid/src/DualOTComputation.py official repository ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 51d6e0cca71c1098 · report
compute_dual j-geuter/sinkhornnnhybrid/src/DualOTComputation.py official repository ran · fixture could not drive it fingerprinted GPL-3.0 (copyleft) · pointer only · 528d87f6039b7d01 · report
compute_mean_conf j-geuter/sinkhornnnhybrid/src/DualOTComputation.py official repository ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 05e10621081d078c · report
euclidean_cost_matrix j-geuter/sinkhornnnhybrid/src/DualOTComputation.py official repository ran · honoured contract GPL-3.0 (copyleft) · pointer only · 2e3c6bac8ba5a4ed · report
genNet j-geuter/sinkhornnnhybrid/src/DualOTComputation.py official repository ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 95e571cd400a1a81 · report
DualApproximator j-geuter/sinkhornnnhybrid/src/DualOTComputation.py official repository unverified GPL-3.0 (copyleft) · pointer only · 33e6b50f0e28481d · report
compute_c_transform j-geuter/sinkhornnnhybrid/src/DualOTComputation.py official repository unverified GPL-3.0 (copyleft) · pointer only · d5fb605e7c5eadce · report
visualize_data j-geuter/sinkhornnnhybrid/src/DualOTComputation.py official repository unverified GPL-3.0 (copyleft) · pointer only · c297c54253d23871 · report
apply_fno gregorkornhardt/unot/src/evaluation/import_models.py found in paper text by Syntology ran · fixture could not drive it MIT (permissive) · 8e17cd361d92ac5a · report
get_dtype gregorkornhardt/unot/scripts/main_neural_operator.py found in paper text by Syntology ran · our draft was wrong MIT (permissive) · ee3fdbef6881a440 · report
neural_operator_input_channel gregorkornhardt/unot/scripts/main_neural_operator.py found in paper text by Syntology ran · honoured contract MIT (permissive) · 1b76b603bd15fed0 · report
load_fno gregorkornhardt/unot/src/evaluation/import_models.py found in paper text by Syntology unverified MIT (permissive) · f741338ad31ffb3f · report
load_mlp gregorkornhardt/unot/src/evaluation/import_models.py found in paper text by Syntology unverified MIT (permissive) · 1cb8e93d593a2908 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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