Papers › Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
Valentin De Bortoli, James Thornton, Jeremy Heng, Arnaud Doucet
Progressively applying Gaussian noise transforms complex data distributions to approximately Gaussian. Reversing this dynamic defines a generative model. When the forward noising process is given by a Stochastic Differential Equation (SDE), Song et al. (2021) demonstrate how the time inhomogeneous drift of the associated reverse-time SDE may be estimated using score-matching. A limitation of this approach is that the forward-time SDE must be run for a sufficiently long time for the final distribution to be approximately Gaussian. In contrast, solving the Schrödinger Bridge problem (SB), i.e. an entropy-regularized optimal transport problem on path spaces, yields diffusions which generate samples from the data distribution in finite time. We present Diffusion SB (DSB), an original approximation of the Iterative Proportional Fitting (IPF) procedure to solve the SB problem, and provide theoretical analysis along with generative modeling experiments. The first DSB iteration recovers the methodology proposed by Song et al. (2021), with the flexibility of using shorter time intervals, as subsequent DSB iterations reduce the discrepancy between the final-time marginal of the forward (resp. backward) SDE with respect to the prior (resp. data) distribution. Beyond generative modeling, DSB offers a widely applicable computational optimal transport tool as the continuous state-space analogue of the popular Sinkhorn algorithm (Cuturi, 2013).
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):
get_harvested_code_for_paper(arxiv_id="2106.01357")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2106.01357", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2106.01357")
Code
Syntology 35 code samples harvested from 2 repositories linked to this paper: 22 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 5 honoured, 2 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 12 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 23 samples from 1 repository, 16 ran (6 with no instrument failure; 10 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.
Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
35 samples harvested: 22 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 5 honoured, 2 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 13 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.
Licence: 0 of the 35 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.
e4c94ae30f27ac18 · report
fixture: returned CacheLoader · level recorded 2026-09-22 c88909f2cfb2fb91 · report
fixture: returned Langevin · level recorded 2026-09-22 5537e783e5bad68a · report
fixture: returned Stacked_MNIST · level recorded 2026-09-22 55327fa0ee65d637 · report
fixture: signature npar:int/0/int, data:str/0/str · returned Tensor · level recorded 2026-09-22 f63e44465df9dea5 · report
fixture: signature x:Tensor/2/float, m:Tensor/2/float, var:Tensor/2/float · returned Tensor · level recorded 2026-09-22 8dbe5289e0087ca3 · report
fixture: signature npar:int/0/int, data_tag:str/0/str · returned TensorDataset · level recorded 2026-09-22 047f2e89ba81227d · report
b15b7368db6c2575 · report
ce40987a5f51f481 · report
dff092e26328f464 · report
fixture: signature b_samples:Tensor/2/float, mean_ideal:ndarray/1/float, cov_ideal:ndarray/2/float · returned complex128 · level recorded 2026-09-22 621c3b5c6259b97e · report
fixture: signature mean_ideal:matrix/2/float, mean_ours:matrix/2/float, cov_ideal:matrix/2/float, cov_ours:matrix/2/float · returned float64 · level recorded 2026-09-22 8d8cecbcb2f02933 · report
fixture: returned EMAHelper · level recorded 2026-09-22 2f94bf4947f9510a · report
fixture: returned Langevin · level recorded 2026-09-22 07ab67e31f0a2c0e · report
fixture: signature state_dict:dict/0/? · returned OrderedDict · level recorded 2026-09-22 2f48cf5e340d5036 · report
fixture: signature dim:int/0/int, seed:int/0/int · returned tuple · level recorded 2026-09-22 f5b271662945056a · report
fixture: signature list_cov:list/1/ndarray, weights:ndarray/1/float, dim:int/0/int · returned matrix · level recorded 2026-09-22 7542200a9ef8296f · report
fixture: signature b_samples:Tensor/2/float · returned ndarray · level recorded 2026-09-22 d602cc73ac0424e5 · report
fixture: signature npar:int/0/int, dim:int/0/int, seed:int/0/int · returned tuple · level recorded 2026-09-22 1365335a7bfbbec5 · report
fixture: signature npar:int/0/int, dim:int/0/int, seed:int/0/int · returned tuple · level recorded 2026-09-22 446d5ae9b2d8c92a · report
fixture: signature args:Args/0/?, data_label:int/0/int · returned tuple · level recorded 2026-09-22 77e8834da5dd3a78 · report
fixture: signature net_f:callable/0/?, net_b:callable/0/?, lr:float/0/float · returned tuple · level recorded 2026-09-22 774e6c73d0322778 · report
fixture: signature dim:int/0/int, random_state:int/0/int, range_sing:list/1/float · returned ndarray · level recorded 2026-09-22 9b452f0316038a1c · report
fixture: signature b_samples:Tensor/2/float · returned tuple · level recorded 2026-09-22 dd8c818eaa83ebdb · report
fixture: signature b_samples:Tensor/2/float · returned ndarray · level recorded 2026-09-22 b1412751e093dbe6 · report
fixture: signature data_loader:DataLoader/0/? · returned generator · level recorded 2026-09-22 30064cd4e8da4011 · report
61f03451a0338d12 · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
2 sibling assemblies for Diffusion Schrödinger Bridge (DSB) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Diffusion Schrödinger Bridge (DSB) (graph method: Diffusion Schrödinger Bridge (DSB)). 23 bricks; individually on a fixture: 16 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.
one of 2 siblings
- IPFTree entry · level 0 · unverified ·
462bbf0816d5e3bf - BW2_UVP helper · level 1 · ran · violated contract ·
dff092e26328f464 - EMAHelper helper · level 1 · ran ·
8d8cecbcb2f02933 - IPFSequential helper · level 0 · unverified ·
5fa86b3b59f03ef2 - cov_ideal helper · level 1 · ran · our draft was wrong ·
f5b271662945056a - get_models helper · level 0 · unverified ·
61f03451a0338d12 - get_tree helper · level 0 · unverified ·
24255e007571b204 - mean_cov_from_samples helper · level 1 · ran · our draft was wrong ·
9b452f0316038a1c - repeater helper · level 1 · ran · our draft was wrong ·
b1412751e093dbe6 - BW2_distance helper · level 1 · ran · violated contract ·
621c3b5c6259b97e - IPFBase helper · level 0 · unverified ·
2053b848ea398325 - cov_real helper · level 1 · ran · honoured contract ·
7542200a9ef8296f - mean_real helper · level 1 · ran · honoured contract ·
dd8c818eaa83ebdb - Langevin sampler · level 1 · ran ·
2f94bf4947f9510a - add_module_state_dict helper · level 1 · ran · our draft was wrong ·
07ab67e31f0a2c0e - get_dataset helper · level 1 · ran · our draft was wrong ·
446d5ae9b2d8c92a - get_logger helper · level 0 · unverified ·
30064cd4e8da4011 - get_optimizers helper · level 1 · ran · our draft was wrong ·
77e8834da5dd3a78 - get_plotter helper · level 0 · unverified ·
06eaaa03d0e243e5 - gaussian_ds helper · level 1 · ran · our draft was wrong ·
1365335a7bfbbec5 - data_distrib helper · level 1 · ran · our draft was wrong ·
d602cc73ac0424e5 - centered_mean_and_covariance helper · level 1 · ran · our draft was wrong ·
2f48cf5e340d5036 - given_singular_spd_cov helper · level 1 · ran; the contract check could not run (RAISES) ·
774e6c73d0322778
harvested Assembly for Diffusion Schrödinger Bridge (DSB) (graph method: Diffusion Schrödinger Bridge (DSB)). 15 bricks; individually on a fixture: 9 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.
one of 2 siblings
- IPFSequential entry · level 0 · unverified ·
6da2149bcace3567 - IPFBase helper · level 0 · unverified ·
3e2072a73ea85aee - CacheLoader helper · level 1 · ran ·
e4c94ae30f27ac18 - EMAHelper helper · level 1 · ran ·
8d8cecbcb2f02933 - Langevin sampler · level 1 · ran ·
c88909f2cfb2fb91 - get_datasets helper · level 0 · unverified ·
047f2e89ba81227d - get_logger helper · level 0 · unverified ·
b15b7368db6c2575 - get_models helper · level 0 · unverified ·
ce40987a5f51f481 - get_optimizers helper · level 1 · ran · our draft was wrong ·
77e8834da5dd3a78 - get_plotter helper · level 0 · unverified ·
a6ba07d0c9906f3c - repeater helper · level 1 · ran · our draft was wrong ·
b1412751e093dbe6 - grad_gauss helper · level 1 · ran · honoured contract ·
f63e44465df9dea5 - Stacked_MNIST helper · level 1 · ran ·
5537e783e5bad68a - two_dim_ds helper · level 1 · ran · honoured contract ·
8dbe5289e0087ca3 - data_distrib helper · level 1 · ran · honoured contract ·
55327fa0ee65d637
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2106.01357") returns these assemblies with each brick's role and wiring (how to connect).
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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