Papers › Robust Compressed Sensing using Generative Models

Robust Compressed Sensing using Generative Models

16 Jun 2020NeurIPS 2020 12arXiv:2006.09461archive 2025-07-28

Ajil Jalal, Liu Liu, Alexandros G. Dimakis, Constantine Caramanis

The goal of compressed sensing is to estimate a high dimensional vector from an underdetermined system of noisy linear equations. In analogy to classical compressed sensing, here we assume a generative model as a prior, that is, we assume the vector is represented by a deep generative model G: ℝᵏ →ℝⁿ. Classical recovery approaches such as empirical risk minimization (ERM) are guaranteed to succeed when the measurement matrix is sub-Gaussian. However, when the measurement matrix and measurements are heavy-tailed or have outliers, recovery may fail dramatically. In this paper we propose an algorithm inspired by the Median-of-Means (MOM). Our algorithm guarantees recovery for heavy-tailed data, even in the presence of outliers. Theoretically, our results show our novel MOM-based algorithm enjoys the same sample complexity guarantees as ERM under sub-Gaussian assumptions. Our experiments validate both aspects of our claims: other algorithms are indeed fragile and fail under heavy-tailed and/or corrupted data, while our approach exhibits the predicted robustness.

PaperPDFConference PDFCodeCode 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 17 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 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: 17 samples from 1 repository, 15 ran (12 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ajiljalal/csgm-robust-neurips officialmentioned in paperpytorchMITSyntology: 17 samples, 15 ran (3 instrument-failed) · 2 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

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
1ran; the contract check could not run
12ran
2unverified

Licence: 1 of the 17 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 ajiljalal/csgm-robust-neurips. “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.

ajiljalal/csgm-robust-neurips official repository 17 samples, 15 ran (3 instrument-failed) · 2 unverified
find_overlap_idx src/create_scripts.py ran MIT (permissive) · 86c8f09d190ff0de · report fixture: signature list_of_strs:list/1/str, str_to_search:str/0/str · returned int · level recorded 2026-09-25
get_figsize in 5 papers src/metrics_utils.py ran MIT (permissive) · 857ba6b23095a4f0 · report fixture: signature is_save:bool/0/bool · returned list · level recorded 2026-09-26
get_full_input src/celebA_input.py ran MIT (permissive) · 68230c4c69e10d9c · report fixture: signature hparams:HParams/0/? · returned dict · level recorded 2026-09-25
get_image_nums src/view_estimated_celebA.py ran MIT (permissive) · 8ad7897be275437c · report fixture: signature start:int/0/int, stop:int/0/int, hparams:HParams/0/? · returned list · level recorded 2026-09-26
get_l2_loss src/utils.py ran MIT (permissive) · 3f8654a051989cdf · report fixture: signature image1:ndarray/4/float, image2:ndarray/4/float · returned float32 · level recorded 2026-09-25
get_measurement_loss src/utils.py ran MIT (permissive) · 9b90a29baade3892 · report fixture: signature x_hat:ndarray/2/float, A:ndarray/2/float, y:ndarray/1/float, hparams:HParams/0/? · returned float64 · level recorded 2026-09-25
get_setting_specific_name src/create_scripts.py ran MIT (permissive) · 09306559529f51d8 · report fixture: signature setting_dict:dict/0/? · returned str · level recorded 2026-09-25
int_or_float in 5 papers src/metrics_utils.py ran MIT (permissive) · 3a73f73ee48b894d · report fixture: signature val:str/0/str · returned int · level recorded 2026-09-25
model_input src/celebA_input.py ran MIT (permissive) · b798a88c68cffe05 · report fixture: signature hparams:HParams/0/? · returned dict · level recorded 2026-09-25
scale in 38 papers src/celebA_utils.py ran fingerprinted MIT (permissive) · 97498d6181a0d2bd · report fixture: signature image:Tensor/2/float · returned Tensor · level recorded 2026-09-25
score_2afc_dataset in 18 papers src/lpips/dist_model.py ran · our draft was wrong MIT (permissive) · 514dd3c0eee3691c · report fixture: signature data_loader:CustomDatasetDataLoader/0/?, func:callable/0/?, name:str/0/str · returned tuple · level recorded 2026-09-25
score_jnd_dataset in 10 papers src/lpips/dist_model.py ran MIT (permissive) · 581c80d602289d6d · report fixture: signature data_loader:MockDataLoader/0/?, func:callable/0/?, name:str/0/str · returned tuple · level recorded 2026-09-25
spatial_average in 34 papers src/lpips/networks_basic.py ran · our draft was wrong fingerprinted MIT (permissive) · 29e5e72bcd006dcd · report fixture: signature in_tens:Tensor/4/float, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-22
transpose in 53 papers
census: 6 implementations from 13 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
src/celebA_utils.py ran fingerprinted MIT (permissive) · a6f71674cdc73691 · report fixture: signature image:ndarray/3/float · returned ndarray · level recorded 2026-09-25
upsample in 87 papers
census: 11 implementations from 16 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
src/lpips/networks_basic.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 351677a36e1961df · report fixture: signature in_tens:Tensor/4/float, out_H:int/0/int · returned Tensor · level recorded 2026-09-24
get_lpips_score src/utils.py unverified MIT (permissive) · f4a3a0cbedef7288 · report
sample_generator_images src/celebA_input.py unverified MIT (permissive) · 29a7a66a98bbc2ed · report

Tasks

compressed sensing

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