Papers › Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems

Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems

18 Jun 2022arXiv:2206.09104archive 2025-07-28

Giannis Daras, Yuval Dagan, Alexandros G. Dimakis, Constantinos Daskalakis

We prove fast mixing and characterize the stationary distribution of the Langevin Algorithm for inverting random weighted DNN generators. This result extends the work of Hand and Voroninski from efficient inversion to efficient posterior sampling. In practice, to allow for increased expressivity, we propose to do posterior sampling in the latent space of a pre-trained generative model. To achieve that, we train a score-based model in the latent space of a StyleGAN-2 and we use it to solve inverse problems. Our framework, Score-Guided Intermediate Layer Optimization (SGILO), extends prior work by replacing the sparsity regularization with a generative prior in the intermediate layer. Experimentally, we obtain significant improvements over the previous state-of-the-art, especially in the low measurement regime.

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

The archive's official repository (giannisdaras/sgilo) was not harvested; the 14 samples below come from 1 community repository.

Syntology 14 code samples harvested from 1 repository linked to this paper: 9 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 1 repository, 9 ran (6 with no instrument failure; 3 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.

giannisdaras/sgilo officialmentioned in papermentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
giannisdaras/ilo mentioned on GitHubpytorchSyntology: 14 samples, 9 ran (3 instrument-failed) · 5 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

14 samples harvested: 9 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 5 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 · our draft was wrong
6ran
5unverified

Licence: 14 of the 14 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 giannisdaras/ilo. “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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

giannisdaras/ilo community (archive-listed) 14 samples, 9 ran (3 instrument-failed) · 5 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
ilo_biggan.py ran no licence file found · pointer only · 0eda3d4423cde1b8 · report fixture: returned Attention · level recorded 2026-09-22
Generator in 95 papers ilo_biggan.py ran no licence file found · pointer only · 99138de6bd7cae2c · report fixture: returned Generator · level recorded 2026-09-22
SNConv2d ilo_biggan.py ran fingerprinted no licence file found · pointer only · d351a46e9a06da43 · report fixture: returned SNConv2d · level recorded 2026-09-22
SNLinear ilo_biggan.py ran no licence file found · pointer only · 12afcd471b0259b3 · report fixture: returned SNLinear · level recorded 2026-09-22
bn in 19 papers ilo_biggan.py ran fingerprinted no licence file found · pointer only · 681a8a8bb1689e7a · report fixture: returned bn · level recorded 2026-09-22
ccbn ilo_biggan.py ran no licence file found · pointer only · efc12d3d5fb6827e · report fixture: returned ccbn · level recorded 2026-09-22
get_transformation ilo_biggan.py ran · our draft was wrong no licence file found · pointer only · f86774a1a092619b · report fixture: signature image_size:int/0/int · returned Compose · level recorded 2026-09-22
join_strings ilo_biggan.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 7122d07d4047b8cf · report fixture: signature base_string:str/0/str, strings:list/1/str · returned str · level recorded 2026-09-22
prepare_z_y ilo_biggan.py ran · our draft was wrong no licence file found · pointer only · 7afc86374d94fbc0 · report fixture: signature G_batch_size:int/0/int, dim_z:int/0/int, nclasses:int/0/int, device:str/0/str, fp16:bool/0/bool, z_var:float/0/float, target:NoneType/0/?, range:NoneType/0/? · returned tuple · level recorded 2026-09-22
BigGAN ilo_biggan.py unverified no licence file found · pointer only · 7196f7ae327ebc54 · report
GBlock in 8 papers ilo_biggan.py unverified no licence file found · pointer only · 1aa1a38d61f04f79 · report
LatentOptimizer ilo_biggan.py unverified no licence file found · pointer only · c6744111e5210552 · report
PerceptualLoss in 5 papers ilo_biggan.py unverified no licence file found · pointer only · c98087bfd5300cf3 · report
load_weights in 35 papers ilo_biggan.py unverified no licence file found · pointer only · d71e48161b7684b4 · 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 Score-Guided Intermediate Layer Optimization (SGILO) (graph method: Score-Guided Intermediate Layer Optimization (SGILO)). 24 bricks; individually on a fixture: 15 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. LatentOptimizer entry · level 0 · unverified · c6744111e5210552
  2. BigGAN model · level 0 · unverified · 7196f7ae327ebc54
  3. PerceptualLoss helper · level 0 · unverified · c98087bfd5300cf3
  4. get_transformation data_transform · level 1 · ran · our draft was wrong · f86774a1a092619b
  5. prepare_z_y helper · level 1 · ran · our draft was wrong · 7afc86374d94fbc0
  6. Generator helper · level 1 · ran · 99138de6bd7cae2c
  7. load_weights helper · level 0 · unverified · d71e48161b7684b4
  8. Attention helper · level 1 · ran · 0eda3d4423cde1b8
  9. GBlock helper · level 0 · unverified · 1aa1a38d61f04f79
  10. G_arch helper · level 1 · ran · our draft was wrong · e8c308c9283407d7
  11. SNConv2d helper · level 1 · ran · d351a46e9a06da43
  12. SNLinear helper · level 1 · ran · 12afcd471b0259b3
  13. bn helper · level 1 · ran · 681a8a8bb1689e7a
  14. ccbn helper · level 1 · ran · efc12d3d5fb6827e
  15. identity helper · level 1 · ran · 33db4a84b81bd4ff
  16. join_strings helper · level 1 · ran · our draft was wrong · 7122d07d4047b8cf
  17. SN helper · level 0 · unverified · b6095d8ef493ff98
  18. myBN helper · level 0 · unverified · ea9320becfdf5158
  19. groupnorm helper · level 1 · ran; the contract check could not run · ed7234a97840eda8
  20. power_iteration helper · level 1 · ran · our draft was wrong · 9d88cf6296bed90f
  21. fused_bn helper · level 1 · ran · honoured contract · d7c46b2392abf5fd
  22. manual_bn helper · level 0 · unverified · 08f41f3d614b0bb9
  23. gram_schmidt helper · level 1 · ran · our draft was wrong · c41836f3e51fa8f1
  24. proj helper · level 0 · unverified · 4015ab1f3ab9b881

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="2206.09104") 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.

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