Papers › Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
Abhimanyu Rajeshkumar Bambhaniya, Amir Yazdanbakhsh, Suvinay Subramanian, Sheng-Chun Kao, Shivani Agrawal, Utku Evci, Tushar Krishna
N:M Structured sparsity has garnered significant interest as a result of relatively modest overhead and improved efficiency. Additionally, this form of sparsity holds considerable appeal for reducing the memory footprint owing to their modest representation overhead. There have been efforts to develop training recipes for N:M structured sparsity, they primarily focus on low-sparsity regions (∼50%). Nonetheless, performance of models trained using these approaches tends to decline when confronted with high-sparsity regions (>80%). In this work, we study the effectiveness of existing sparse training recipes at high-sparsity regions and argue that these methods fail to sustain the model quality on par with low-sparsity regions. We demonstrate that the significant factor contributing to this disparity is the presence of elevated levels of induced noise in the gradient magnitudes. To mitigate this undesirable effect, we employ decay mechanisms to progressively restrict the flow of gradients towards pruned elements. Our approach improves the model quality by up to 2% and 5% in vision and language models at high sparsity regime, respectively. We also evaluate the trade-off between model accuracy and training compute cost in terms of FLOPs. At iso-training FLOPs, our method yields better performance compared to conventional sparse training recipes, exhibiting an accuracy improvement of up to 2%. The source code is available at https://github.com/abhibambhaniya/progressive_gradient_flow_nm_sparsity.
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):
get_harvested_code_for_paper(arxiv_id="2402.04744")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2402.04744", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2402.04744")
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; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 7 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 (5 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 15 samples that ran have no recorded date.
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; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 10 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.
Licence: 0 of the 17 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 abhibambhaniya/progressive_gradient_flow_nm_sparsity. “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.
410bffb8a07b52e3 · report
fixture: signature model:callable/0/? · returned int · level recorded, date not recorded 33bca8cbc866bf64 · report
fixture: signature checkpoint_path:str/0/str · returned float · level recorded 2026-09-24 e69e9b0108bef81c · report
fixture: signature args:MockArgs/0/? · returned tuple · level recorded 2026-09-24 50d653ee6a59955c · report
fixture: signature sync:bool/0/bool, device:NoneType/0/? · returned float · level recorded, date not recorded 91c27523dde7eb4a · report
fixture: returned Tensor · level recorded 2026-09-24 5bed58ca17652913 · report
fixture: signature mx_name:str/0/str · returned str · level recorded 2026-09-24 census: 5 implementations from 8 papers, 1 distinct output on one shared input timm/layers/activations.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) ·
801c85b8903bfff5 · report
fixture: signature x:Tensor/2/float, inplace:bool/0/bool · returned Tensor · level recorded 2026-09-24 14eddd8cc4c65fe0 · report
fixture: returned Tensor · level recorded 2026-09-24 census: 36 implementations from 56 papers, 7 distinct outputs across 3 buckets, one shared input per bucket timm/layers/activations.py ran fingerprinted Apache-2.0 (permissive) ·
d83b6ecf3cdc1d6a · report
fixture: signature x:Tensor/2/float, inplace:bool/0/bool · returned Tensor · level recorded 2026-09-24 census: 14 implementations from 37 papers, 2 distinct outputs on one shared input timm/layers/activations.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) ·
717e4d22b6d103e6 · report
fixture: signature x:Tensor/2/float, inplace:bool/0/bool · returned Tensor · level recorded 2026-09-24 8e341f8585b3fe94 · report
fixture: returned Tensor · level recorded 2026-09-24 ccf59d4aa2ccacdb · report
fixture: returned Tensor · level recorded 2026-09-24 2d53e47b891cd927 · report
fixture: returned Tensor · level recorded 2026-09-24 51a2f9920a170144 · report
fixture: returned Tensor · level recorded 2026-09-24 475160c5a1a1225a · report
fixture: signature sync:bool/0/bool · returned float · level recorded, date not recorded Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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