Papers › Guided Diffusion Sampling on Function Spaces with Applications to PDEs

Guided Diffusion Sampling on Function Spaces with Applications to PDEs

22 May 2025arXiv:2505.17004archive 2025-07-28

Jiachen Yao, Abbas Mammadov, Julius Berner, Gavin Kerrigan, Jong Chul Ye, Kamyar Azizzadenesheli, Anima Anandkumar

We propose a general framework for conditional sampling in PDE-based inverse problems, targeting the recovery of whole solutions from extremely sparse or noisy measurements. This is accomplished by a function-space diffusion model and plug-and-play guidance for conditioning. Our method first trains an unconditional discretization-agnostic denoising model using neural operator architectures. At inference, we refine the samples to satisfy sparse observation data via a gradient-based guidance mechanism. Through rigorous mathematical analysis, we extend Tweedie's formula to infinite-dimensional Hilbert spaces, providing the theoretical foundation for our posterior sampling approach. Our method (FunDPS) accurately captures posterior distributions in function spaces under minimal supervision and severe data scarcity. Across five PDE tasks with only 3% observation, our method achieves an average 32% accuracy improvement over state-of-the-art fixed-resolution diffusion baselines while reducing sampling steps by 4x. Furthermore, multi-resolution fine-tuning ensures strong cross-resolution generalizability. To the best of our knowledge, this is the first diffusion-based framework to operate independently of discretization, offering a practical and flexible solution for forward and inverse problems in the context of PDEs. Code is available at https://github.com/neuraloperator/FunDPS

PaperPDFCodeCode Syntology ranMethod as code

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 26 code samples harvested from 1 repository linked to this paper: 19 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 8 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 26 samples from 1 repository, 19 ran (9 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.

neuraloperator/fundps officialmentioned in papermentioned on GitHubpytorchMITSyntology: 26 samples, 19 ran (10 instrument-failed) · 7 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

26 samples harvested: 19 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 7 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.

3ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
8ran; the contract check could not run
5ran
7unverified

Licence: 0 of the 26 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 neuraloperator/fundps. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

neuraloperator/fundps official repository 26 samples, 19 ran (10 instrument-failed) · 7 unverified
DatasetNormalizer generation/dps.py ran MIT (permissive) · a764c92b51887090 · report fixture: returned DatasetNormalizer · level recorded 2026-09-22
FullObservation generation/dps.py ran MIT (permissive) · 607661f0464669d6 · report fixture: returned FullObservation · level recorded 2026-09-22
Observation generation/dps.py ran MIT (permissive) · 1281fa90656c411b · report fixture: returned Observation · level recorded 2026-09-22
PDEDataset generation/dps.py ran MIT (permissive) · 9ad0358dd430c924 · report fixture: returned PDEDataset · level recorded 2026-09-22
RBFKernel generation/dps.py ran MIT (permissive) · 55a5bbf6c6f4dea1 · report fixture: returned RBFKernel · level recorded 2026-09-22
batched_loss generation/dps.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · f6f36fd9d354adad · report fixture: signature x:Tensor/4/float, n_obs:int/0/int · returned Tensor · level recorded 2026-09-22
get_burgers_residual generation/dps.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 2c86054a4f79a831 · report fixture: signature x_pred:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_darcy_residual generation/dps.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 336217453f6a14d2 · report fixture: signature x_pred:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_fixed_coords generation/dps.py ran · honoured contract MIT (permissive) · 1cc6a2ab17c9f3e2 · report fixture: signature Ln1:int/0/int, Ln2:int/0/int · returned Tensor · level recorded 2026-09-22
get_helmholtz_residual generation/dps.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 132b513b6ea8e67b · report fixture: signature x_pred:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_loss_func in 26 papers generation/dps.py ran · our draft was wrong MIT (permissive) · 507e51ab566b1005 · report fixture: signature loss_type:str/0/str · returned function · level recorded 2026-09-22
get_ns_bounded_residual generation/dps.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 3b03fab64964340f · report fixture: signature x_pred:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_ns_nonbounded_residual generation/dps.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · fb5f9dc83a09ffa0 · report fixture: signature x_pred:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_poisson_residual generation/dps.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 7eea8f617cd78cdc · report fixture: signature x_pred:Tensor/4/float · returned Tensor · level recorded 2026-09-22
huber_loss in 34 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket this sample: bucket 5 of 5, arg 1: rank 4, kind float, dtype float32
generation/dps.py ran · our draft was wrong fingerprinted MIT (permissive) · ab891ef221209094 · report fixture: signature x:Tensor/4/float, n_obs:int/0/int, delta:float/0/float · returned Tensor · level recorded 2026-09-22
l1_loss in 149 papers
census: 3 implementations from 7 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 3 of 3, arg 1: rank 4, kind float, dtype float32
generation/dps.py ran · honoured contract fingerprinted MIT (permissive) · e90ea3b7b0c4106e · report fixture: signature x:Tensor/4/float, n_obs:int/0/int · returned Tensor · level recorded 2026-09-22
l2_loss in 136 papers generation/dps.py ran · honoured contract fingerprinted MIT (permissive) · 033caf372281941b · report fixture: signature x:Tensor/4/float, n_obs:int/0/int · returned Tensor · level recorded 2026-09-22
mse_loss in 73 papers
census: 8 implementations from 12 papers, 6 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 4 of 4, arg 1: rank 4, kind float, dtype float32
generation/dps.py ran · violated contract fingerprinted MIT (permissive) · 8be214b363325c85 · report fixture: signature x:Tensor/4/float, n_obs:int/0/int · returned Tensor · level recorded 2026-09-22
transform_darcy generation/dps.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · fcb362bbb769848b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
NoiseSampler generation/dps.py unverified MIT (permissive) · a1ad6aa95472bdcd · report
PDEObservation generation/dps.py unverified MIT (permissive) · f1e50f2f0c3eb299 · report
PDESolver generation/dps.py unverified MIT (permissive) · 187875e852c295f0 · report
PDESolverDPS generation/dps.py unverified MIT (permissive) · 831b22b68d561737 · report
SparseObservation generation/dps.py unverified MIT (permissive) · ee86e31974265100 · report
get_observation_class generation/dps.py unverified MIT (permissive) · 892f92a74b9d2bfb · report
get_pde_residual generation/dps.py unverified MIT (permissive) · f933ac4c89aec5c5 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for FunDPS (graph method: FunDPS). 26 bricks; individually on a fixture: 19 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. PDESolverDPS entry · level 0 · unverified · 831b22b68d561737
  2. PDESolver helper · level 0 · unverified · 187875e852c295f0
  3. PDEDataset helper · level 1 · ran · 9ad0358dd430c924
  4. RBFKernel helper · level 1 · ran · 55a5bbf6c6f4dea1
  5. get_observation_class helper · level 0 · unverified · 892f92a74b9d2bfb
  6. DatasetNormalizer helper · level 1 · ran · a764c92b51887090
  7. NoiseSampler helper · level 0 · unverified · a1ad6aa95472bdcd
  8. get_fixed_coords helper · level 1 · ran · honoured contract · 1cc6a2ab17c9f3e2
  9. FullObservation helper · level 1 · ran · 607661f0464669d6
  10. PDEObservation helper · level 0 · unverified · f1e50f2f0c3eb299
  11. SparseObservation helper · level 0 · unverified · ee86e31974265100
  12. transform_darcy helper · level 1 · ran; the contract check could not run (RAISES) · fcb362bbb769848b
  13. Observation helper · level 1 · ran · 1281fa90656c411b
  14. get_pde_residual helper · level 0 · unverified · f933ac4c89aec5c5
  15. get_loss_func helper · level 1 · ran · our draft was wrong · 507e51ab566b1005
  16. get_burgers_residual helper · level 1 · ran; the contract check could not run (RAISES) · 2c86054a4f79a831
  17. get_darcy_residual helper · level 1 · ran; the contract check could not run (RAISES) · 336217453f6a14d2
  18. get_helmholtz_residual helper · level 1 · ran; the contract check could not run (RAISES) · 132b513b6ea8e67b
  19. get_ns_bounded_residual helper · level 1 · ran; the contract check could not run (RAISES) · 3b03fab64964340f
  20. get_ns_nonbounded_residual helper · level 1 · ran; the contract check could not run (RAISES) · fb5f9dc83a09ffa0
  21. get_poisson_residual helper · level 1 · ran; the contract check could not run (RAISES) · 7eea8f617cd78cdc
  22. batched_loss helper · level 1 · ran; the contract check could not run (RAISES) · f6f36fd9d354adad
  23. huber_loss helper · level 1 · ran · our draft was wrong · ab891ef221209094
  24. l1_loss helper · level 1 · ran · honoured contract · e90ea3b7b0c4106e
  25. l2_loss helper · level 1 · ran · honoured contract · 033caf372281941b
  26. mse_loss helper · level 1 · ran · violated contract · 8be214b363325c85

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="2505.17004") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Denoising

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