Papers › Variational Diffusion Posterior Sampling with Midpoint Guidance

Variational Diffusion Posterior Sampling with Midpoint Guidance

13 Oct 2024arXiv:2410.09945archive 2025-07-28

Badr Moufad, Yazid Janati, Lisa Bedin, Alain Durmus, Randal Douc, Eric Moulines, Jimmy Olsson

Diffusion models have recently shown considerable potential in solving Bayesian inverse problems when used as priors. However, sampling from the resulting denoising posterior distributions remains a challenge as it involves intractable terms. To tackle this issue, state-of-the-art approaches formulate the problem as that of sampling from a surrogate diffusion model targeting the posterior and decompose its scores into two terms: the prior score and an intractable guidance term. While the former is replaced by the pre-trained score of the considered diffusion model, the guidance term has to be estimated. In this paper, we propose a novel approach that utilises a decomposition of the transitions which, in contrast to previous methods, allows a trade-off between the complexity of the intractable guidance term and that of the prior transitions. We validate the proposed approach through extensive experiments on linear and nonlinear inverse problems, including challenging cases with latent diffusion models as priors. We then demonstrate its applicability to various modalities and its promising impact on public health by tackling cardiovascular disease diagnosis through the reconstruction of incomplete electrocardiograms. The code is publicly available at \url{https://github.com/yazidjanati/mgps}.

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="2410.09945")

Code

Syntology Ran 12 of 23 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 5 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 23 samples from 1 repository, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yazidjanati/mgps officialmentioned in paperjax 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

23 samples harvested; 12 ran; 0 honoured the contract we drafted; 11 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.

5ran · our draft was wrong
7ran
11unverified

Licence: 23 of the 23 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 yazidjanati/mgps. “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.

fft2c_new yazidjanati/mgps/src/imaging/fastmri_utils.py official repository ran no licence file found · pointer only · dc2dcfd069e89041 · report
get_param_groups_and_shapes yazidjanati/mgps/src/guided_diffusion/fp16_util.py official repository ran no licence file found · pointer only · e41367ad14ff58fd · report
make_master_params yazidjanati/mgps/src/guided_diffusion/fp16_util.py official repository ran no licence file found · pointer only · e20dd5102da3b050 · report
register_conditioning_method yazidjanati/mgps/src/guided_diffusion/condition_methods.py official repository ran · our draft was wrong no licence file found · pointer only · 8027fc71dcbcfc45 · report
register_mean_processor yazidjanati/mgps/src/guided_diffusion/posterior_mean_variance.py official repository ran · our draft was wrong no licence file found · pointer only · 2423fa5313aa3525 · report
register_noise yazidjanati/mgps/src/guided_diffusion/measurements.py official repository ran no licence file found · pointer only · 905f4b0d3baca742 · report
register_operator yazidjanati/mgps/src/guided_diffusion/measurements.py official repository ran no licence file found · pointer only · 7f47ba486efd2c7e · report
register_operator yazidjanati/mgps/src/guided_diffusion/operators_wrappers.py official repository ran no licence file found · pointer only · 559ce6b0ae13e4fd · report
register_sampler yazidjanati/mgps/src/guided_diffusion/gaussian_diffusion.py official repository ran · our draft was wrong no licence file found · pointer only · d9bb4d03137bc7e9 · report
register_var_processor yazidjanati/mgps/src/guided_diffusion/posterior_mean_variance.py official repository ran · our draft was wrong no licence file found · pointer only · e214ee19e7a9d92b · report
unflatten_master_params yazidjanati/mgps/src/guided_diffusion/fp16_util.py official repository ran no licence file found · pointer only · 64fff1e30802b815 · report
zero_module yazidjanati/mgps/src/guided_diffusion/nn.py official repository ran · our draft was wrong no licence file found · pointer only · 129b804760b3115f · report
avg_pool_nd yazidjanati/mgps/src/guided_diffusion/nn.py official repository unverified no licence file found · pointer only · ecd0fc28815b65ae · report
cal_gradient_penalty yazidjanati/mgps/src/guided_diffusion/unet.py official repository unverified no licence file found · pointer only · 944d16b22c6e6e77 · report
conv_nd yazidjanati/mgps/src/guided_diffusion/nn.py official repository unverified no licence file found · pointer only · fe4eb545bbb728e0 · report
create_model yazidjanati/mgps/src/guided_diffusion/unet.py official repository unverified no licence file found · pointer only · 65021ae774b7b013 · report
create_sampler yazidjanati/mgps/src/guided_diffusion/gaussian_diffusion.py official repository unverified no licence file found · pointer only · 7a9479e9edb0166b · report
fft2c_old yazidjanati/mgps/src/imaging/fastmri_utils.py official repository unverified no licence file found · pointer only · d5d761740edb12db · report
get_conditioning_method yazidjanati/mgps/src/guided_diffusion/condition_methods.py official repository unverified no licence file found · pointer only · ceb7328ab8bdbfe2 · report
get_mean_processor yazidjanati/mgps/src/guided_diffusion/posterior_mean_variance.py official repository unverified no licence file found · pointer only · e92451e6fb900818 · report
get_operator yazidjanati/mgps/src/guided_diffusion/measurements.py official repository unverified no licence file found · pointer only · bbb1be64bf961d18 · report
get_sampler yazidjanati/mgps/src/guided_diffusion/gaussian_diffusion.py official repository unverified no licence file found · pointer only · b910fefa7866252e · report
ifft2c_old yazidjanati/mgps/src/imaging/fastmri_utils.py official repository unverified no licence file found · pointer only · d63efa5d2fd536e2 · report

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