Papers › Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark

Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark

16 Jun 2023NeurIPS 2023 11arXiv:2306.10161archive 2025-07-28

Nikita Gushchin, Alexander Kolesov, Petr Mokrov, Polina Karpikova, Andrey Spiridonov, Evgeny Burnaev, Alexander Korotin

Over the last several years, there has been significant progress in developing neural solvers for the Schr\"odinger Bridge (SB) problem and applying them to generative modelling. This new research field is justifiably fruitful as it is interconnected with the practically well-performing diffusion models and theoretically grounded entropic optimal transport (EOT). Still, the area lacks non-trivial tests allowing a researcher to understand how well the methods solve SB or its equivalent continuous EOT problem. We fill this gap and propose a novel way to create pairs of probability distributions for which the ground truth OT solution is known by the construction. Our methodology is generic and works for a wide range of OT formulations, in particular, it covers the EOT which is equivalent to SB (the main interest of our study). This development allows us to create continuous benchmark distributions with the known EOT and SB solutions on high-dimensional spaces such as spaces of images. As an illustration, we use these benchmark pairs to test how well existing neural EOT/SB solvers actually compute the EOT solution. Our code for constructing benchmark pairs under different setups is available at: https://github.com/ngushchin/EntropicOTBenchmark.

PaperPDFConference PDFCodeCode 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="2306.10161")

Code

Syntology Ran 4 of 18 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 3 ran · honoured contract; 1 ran · our draft was wrong.

By repository: official repository: 18 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ngushchin/entropicotbenchmark officialmentioned in papermentioned on GitHubpytorchMIT 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

18 samples harvested; 4 ran; 3 honoured the contract we drafted; 14 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.

3ran · honoured contract
1ran · our draft was wrong
14unverified

Licence: 0 of the 18 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 ngushchin/entropicotbenchmark. “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.

gaussian_log_p ngushchin/entropicotbenchmark/benchmark/glow_model.py official repository ran · honoured contract fingerprinted MIT (permissive) · 0466e4f918aa9da0 · report
gaussian_sample ngushchin/entropicotbenchmark/benchmark/glow_model.py official repository ran · honoured contract fingerprinted MIT (permissive) · 87324754644a55a3 · report
imread ngushchin/entropicotbenchmark/baselines/EntropicNeuralOptimalTransport/src/fid_score.py official repository ran · honoured contract MIT (permissive) · aa4cae054b657ba2 · report
make_net ngushchin/entropicotbenchmark/baselines/EntropicNeuralOptimalTransport/src/enot.py official repository ran · our draft was wrong MIT (permissive) · 6650c402c625ef7c · report
calc_loss ngushchin/entropicotbenchmark/benchmark/glow_train.py official repository unverified MIT (permissive) · 5450899cdebae728 · report
calc_z_shapes ngushchin/entropicotbenchmark/benchmark/glow_train.py official repository unverified MIT (permissive) · f452bf17ed5cad17 · report
calculate_frechet_distance ngushchin/entropicotbenchmark/baselines/EntropicNeuralOptimalTransport/src/fid_score.py official repository unverified MIT (permissive) · 0def50a351111624 · report
compute_BW_by_gt_samples ngushchin/entropicotbenchmark/benchmark/metrics.py official repository unverified MIT (permissive) · 589f3cee2cb326d4 · report
compute_BW_with_gt_stats ngushchin/entropicotbenchmark/benchmark/metrics.py official repository unverified MIT (permissive) · 4007d36e1fe2fe05 · report
get_activations ngushchin/entropicotbenchmark/baselines/EntropicNeuralOptimalTransport/src/fid_score.py official repository unverified MIT (permissive) · 56afde1af5757691 · report
get_data_home ngushchin/entropicotbenchmark/benchmark/auxiliary.py official repository unverified MIT (permissive) · 90deee0d92c78913 · report
get_test_input_samples ngushchin/entropicotbenchmark/benchmark/gaussian_mixture_benchmark.py official repository unverified MIT (permissive) · 140844b4cd5eca26 · report
integrate ngushchin/entropicotbenchmark/baselines/EntropicNeuralOptimalTransport/src/enot.py official repository unverified MIT (permissive) · 3add5b29ad2cbd24 · report
load_input_test_images ngushchin/entropicotbenchmark/benchmark/image_benchmark.py official repository unverified MIT (permissive) · 0ec25b7c244e361d · report
sample_z_list ngushchin/entropicotbenchmark/benchmark/langevin_dynamics.py official repository unverified MIT (permissive) · 0788e1a6bd53e61f · report
symmetrize ngushchin/entropicotbenchmark/benchmark/distributions.py official repository unverified MIT (permissive) · c1eb471d75746958 · report
tensor_list_to_vector ngushchin/entropicotbenchmark/benchmark/langevin_dynamics.py official repository unverified MIT (permissive) · f5d53036927ce313 · report
vector_to_tensor_list ngushchin/entropicotbenchmark/benchmark/langevin_dynamics.py official repository unverified MIT (permissive) · 68f320ab0a24a55b · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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