Papers › Underdamped Diffusion Bridges with Applications to Sampling

Underdamped Diffusion Bridges with Applications to Sampling

2 Mar 2025arXiv:2503.01006archive 2025-07-28

Denis Blessing, Julius Berner, Lorenz Richter, Gerhard Neumann

We provide a general framework for learning diffusion bridges that transport prior to target distributions. It includes existing diffusion models for generative modeling, but also underdamped versions with degenerate diffusion matrices, where the noise only acts in certain dimensions. Extending previous findings, our framework allows to rigorously show that score matching in the underdamped case is indeed equivalent to maximizing a lower bound on the likelihood. Motivated by superior convergence properties and compatibility with sophisticated numerical integration schemes of underdamped stochastic processes, we propose underdamped diffusion bridges, where a general density evolution is learned rather than prescribed by a fixed noising process. We apply our method to the challenging task of sampling from unnormalized densities without access to samples from the target distribution. Across a diverse range of sampling problems, our approach demonstrates state-of-the-art performance, notably outperforming alternative methods, while requiring significantly fewer discretization steps and no hyperparameter tuning.

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 10 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 10 ran (10 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.

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

DenisBless/UnderdampedDiffusionBridges officialjaxMITSyntology: 10 samples, 10 ran (0 instrument-failed) · 0 unverified 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

10 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 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.

10ran

Licence: 1 of the 10 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from DenisBless/UnderdampedDiffusionBridges. “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.

DenisBless/UnderdampedDiffusionBridges official repository 10 samples, 10 ran (0 instrument-failed) · 0 unverified
check_stop_grad algorithms/common/utils.py ran MIT (permissive) · 29ab22cf1e391158 · report fixture: signature expression:ArrayImpl/1/float, stop_grad:bool/0/bool · returned ArrayImpl · level recorded 2026-09-25
get_cosine_schedule algorithms/common/scheduler.py ran MIT (permissive) · 3a7853161909da1d · report fixture: signature total_steps:int/0/int, min:float/0/float, s:float/0/float, pow:int/0/int · returned function · level recorded 2026-09-24
get_learning_rate_scheduler algorithms/common/learning_rate_scheduler.py ran MIT (permissive) · 896621e81a8c000f · report fixture: signature cfg:dict/0/?, step_size:float/0/float · returned function · level recorded 2026-09-25
get_linear_schedule algorithms/common/scheduler.py ran MIT (permissive) · d85b357fbdeb22d7 · report fixture: signature total_steps:int/0/int, min:float/0/float · returned function · level recorded 2026-09-24
init_langevin algorithms/common/init_diffusion_model.py ran MIT (permissive) here; the stored copy is pointer only · d443d828e92a9ae7 · report fixture: signature cfg:Config/0/?, prior_log_prob:callable/0/?, target_log_prob:callable/0/? · returned function · level recorded 2026-09-26
init_underdamped algorithms/common/init_diffusion_model.py ran MIT (permissive) · ec4e879e1a90f33d · report fixture: signature cfg:Config/0/?, dim:int/0/int · returned tuple · level recorded 2026-09-24
neg_elbo algorithms/overdamped/overdamped_rnd.py ran MIT (permissive) · 0a3afc9623a6941a · report fixture: signature key:ArrayImpl/1/int, model_state:ModelState/0/?, params:dict/0/?, integrator:callable/0/?, diffusion_model:DiffusionModel/0/?, batch_size:int/0/int · returned ArrayImpl · level recorded 2026-09-25
per_sample_rnd algorithms/overdamped/overdamped_rnd.py ran MIT (permissive) · 866334c87a4478ef · report fixture: signature seed:ArrayImpl/1/int, model_state:ModelState/0/?, params:Params/0/?, integrator:callable/0/?, diffusion_model:DiffusionModel/0/?, stop_grad:bool/0/bool, eval:bool/0/bool · returned tuple · level recorded 2026-09-24
rnd algorithms/overdamped/overdamped_rnd.py ran MIT (permissive) · 8cce7df513db5677 · report fixture: signature key:ArrayImpl/1/int, model_state:MinimalModelState/0/?, params:dict/0/?, integrator:callable/0/?, diffusion_model:MinimalDiffusionModel/0/?, batch_size:int/0/int, stop_grad:bool/0/bool, eval:bool/0/bool · returned tuple · level recorded 2026-09-24
sample_kernel algorithms/common/utils.py ran MIT (permissive) · 80005c2f78f46bf7 · report fixture: signature rng_key:PRNGKeyArray/0/key<fry>, mean:ArrayImpl/1/float, scale:ArrayImpl/1/float · returned ArrayImpl · level recorded 2026-09-24

Tasks

Numerical Integration

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