Papers › SAMPa: Sharpness-aware Minimization Parallelized

SAMPa: Sharpness-aware Minimization Parallelized

14 Oct 2024arXiv:2410.10683archive 2025-07-28

Wanyun Xie, Thomas Pethick, Volkan Cevher

Sharpness-aware minimization (SAM) has been shown to improve the generalization of neural networks. However, each SAM update requires sequentially computing two gradients, effectively doubling the per-iteration cost compared to base optimizers like SGD. We propose a simple modification of SAM, termed SAMPa, which allows us to fully parallelize the two gradient computations. SAMPa achieves a twofold speedup of SAM under the assumption that communication costs between devices are negligible. Empirical results show that SAMPa ranks among the most efficient variants of SAM in terms of computational time. Additionally, our method consistently outperforms SAM across both vision and language tasks. Notably, SAMPa theoretically maintains convergence guarantees even for fixed perturbation sizes, which is established through a novel Lyapunov function. We in fact arrive at SAMPa by treating this convergence guarantee as a hard requirement -- an approach we believe is promising for developing SAM-based methods in general. Our code is available at https://github.com/LIONS-EPFL/SAMPa.

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.

Syntology holds a reference implementation of SAMPa, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='SAMPa') (how to connect); the free check have('2410.10683') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 13 ran (3 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.

lions-epfl/sampa officialmentioned in papermentioned on GitHubpytorchSyntology: 15 samples, 13 ran (10 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

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 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.

10ran · our draft was wrong
3ran
2unverified

Licence: 15 of the 15 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 lions-epfl/sampa. “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.

lions-epfl/sampa official repository 15 samples, 13 ran (10 instrument-failed) · 2 unverified
DenseNet121 in 32 papers model/densenet.py ran · our draft was wrong no licence file found · pointer only · dfb395bae3d07d76 · report fixture: signature num_classes:int/0/int · returned DenseNet · level recorded 2026-09-24
DenseNet169 in 23 papers model/densenet.py ran · our draft was wrong no licence file found · pointer only · f295fe3c209ecf78 · report fixture: signature num_classes:int/0/int · returned DenseNet · level recorded 2026-09-24
DenseNet201 in 22 papers model/densenet.py ran · our draft was wrong no licence file found · pointer only · 6383aee1c940e7a5 · report fixture: signature num_classes:int/0/int · returned DenseNet · level recorded 2026-09-24
make_layers in 155 papers model/vgg.py ran · our draft was wrong no licence file found · pointer only · ac62432dc5134b0d · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-24
perturbation_loss_log model/smooth_cross_entropy.py ran no licence file found · pointer only · a51802083eb2dcec · report fixture: signature pred:Tensor/2/float, targets:Tensor/1/int, mu:int/0/int, alpha:float/0/float · returned Tensor · level recorded 2026-09-24
resnet20 in 42 papers model/resnet.py ran · our draft was wrong no licence file found · pointer only · a10d10e7bcf4cb4a · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
resnet32 in 47 papers model/resnet.py ran · our draft was wrong no licence file found · pointer only · 85364deb653f2cf6 · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
resnet44 in 19 papers model/resnet.py ran · our draft was wrong no licence file found · pointer only · cd8b7f0a3a1b23f4 · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
smooth_crossentropy in 5 papers model/smooth_cross_entropy.py ran no licence file found · pointer only · 8ba7b4a94a39f790 · report fixture: signature pred:Tensor/2/float, gold:Tensor/1/int, smoothing:float/0/float, perturb_label:float/0/float · returned Tensor · level recorded 2026-09-24
smooth_crossentropy in 5 papers utility.py ran · our draft was wrong no licence file found · pointer only · f86df65986410c1d · report fixture: signature pred:Tensor/2/float, gold:Tensor/1/int, smoothing:float/0/float · returned Tensor · level recorded 2026-09-24
unflatten in 15 papers utility.py ran no licence file found · pointer only · c1ad6496b7bd2b05 · report fixture: signature gradient:Tensor/1/float, parameters:list/1/Tensor · returned list · level recorded 2026-09-24
vgg11 in 50 papers model/vgg.py ran · our draft was wrong no licence file found · pointer only · d61c738bf16ec3c0 · report fixture: signature num_classes:int/0/int · returned VGG · level recorded 2026-09-24
vgg11_bn in 40 papers model/vgg.py ran · our draft was wrong no licence file found · pointer only · 09c336c3ecb596a3 · report fixture: signature num_classes:int/0/int · returned VGG · level recorded 2026-09-24
get_dataset in 285 papers get_dataset.py unverified no licence file found · pointer only · caf601cac7f2ec8c · report
perturbation_loss_tanh model/smooth_cross_entropy.py unverified no licence file found · pointer only · be5e295a85a5ce89 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

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

generated Assembly for SAMPa (graph method: SAMPa), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. sampa_compute_final_gradient entry · level 2 · ran · 7e869acdfb6e9a20ac24d41189b1e031d9b7a5ac84e3233da30ab070c4627800

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="2410.10683") 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.

Methods

BASESAMSGD

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