Papers › Hessian-based Analysis of Large Batch Training and Robustness to Adversaries

Hessian-based Analysis of Large Batch Training and Robustness to Adversaries

22 Feb 2018NeurIPS 2018 12arXiv:1802.08241archive 2025-07-28

Zhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer, Michael W. Mahoney

Large batch size training of Neural Networks has been shown to incur accuracy loss when trained with the current methods. The exact underlying reasons for this are still not completely understood. Here, we study large batch size training through the lens of the Hessian operator and robust optimization. In particular, we perform a Hessian based study to analyze exactly how the landscape of the loss function changes when training with large batch size. We compute the true Hessian spectrum, without approximation, by back-propagating the second derivative. Extensive experiments on multiple networks show that saddle-points are not the cause for generalization gap of large batch size training, and the results consistently show that large batch converges to points with noticeably higher Hessian spectrum. Furthermore, we show that robust training allows one to favor flat areas, as points with large Hessian spectrum show poor robustness to adversarial perturbation. We further study this relationship, and provide empirical and theoretical proof that the inner loop for robust training is a saddle-free optimization problem almost everywhere. We present detailed experiments with five different network architectures, including a residual network, tested on MNIST, CIFAR-10, and CIFAR-100 datasets. We have open sourced our method which can be accessed at [1].

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

No sample from the archive's official repository (amirgholami/pyhessian) is linked to this paper; the 11 samples below come from 2 community repositories. Syntology harvested code from amirgholami/pyhessian for another paper.

amirgholami/pyhessian: Syntology's graph links these samples to PyHessian: Neural Networks Through the Lens of the Hessian (arXiv:1912.07145; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.

Syntology 11 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 2 repositories, 9 ran (7 with no instrument failure; 2 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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.

amirgholami/pyhessian officialpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PyHessian: Neural Networks Through the Lens of the Hessian (arXiv:1912.07145; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
amirgholami/hessianflow mentioned in papermentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
ABadCandy/HessianDL mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
mtkwT/Hessian-analysis-with-tensorflow1.x mentioned on GitHubtfSyntology: not harvested report
mtkwT/Hessian-based-analysis-tensorflow mentioned on GitHubtfSyntology: not harvested report
noahgolmant/pytorch-hessian-eigenthings mentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (0 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 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 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.

2ran · our draft was wrong
7ran
2unverified

Licence: 0 of the 11 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

ABadCandy/HessianDL community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
deflated_power_iteration hessian_eigenthings/power_iter.py ran · our draft was wrong MIT (permissive) · 4532c973ff280886 · report fixture: signature operator:callable/0/?, num_eigenthings:int/0/int, power_iter_steps:int/0/int, power_iter_err_threshold:float/0/float, momentum:float/0/float, use_gpu:bool/0/bool · returned tuple · level recorded 2026-09-22
power_iteration in 30 papers hessian_eigenthings/power_iter.py ran · our draft was wrong MIT (permissive) · 604f7701e0559dac · report fixture: signature operator:SimpleOperator/0/?, steps:int/0/int, error_threshold:float/0/float, momentum:float/0/float, use_gpu:bool/0/bool · returned tuple · level recorded 2026-09-22
noahgolmant/pytorch-hessian-eigenthings community (archive-listed) 9 samples, 7 ran (0 instrument-failed) · 2 unverified
move_batch_to_device hessian_eigenthings/batching.py ran MIT (permissive) · 2aad088de22e5375 · report fixture: signature batch:dict/0/?, device:device/0/? · returned dict · level recorded 2026-09-26
params_to_vector hessian_eigenthings/param_utils.py ran MIT (permissive) · afb38db4bcfbd007 · report fixture: signature params:dict/0/? · returned Tensor · level recorded 2026-09-26
select_parameters hessian_eigenthings/param_utils.py ran MIT (permissive) · 73fdac2eac4bb1ca · report fixture: signature model:callable/0/?, param_filter:callable/0/? · returned dict · level recorded 2026-09-26
supervised_forward hessian_eigenthings/loss_fns/standard.py ran MIT (permissive) · 1ff9aef5e997ef41 · report fixture: signature model:callable/0/?, batch:tuple/1/Tensor · returned Tensor · level recorded 2026-09-26
supervised_loss hessian_eigenthings/loss_fns/standard.py ran MIT (permissive) · 631fe6f0c718ea1f · report fixture: signature criterion:callable/0/? · returned function · level recorded 2026-09-26
supervised_loss_of_output hessian_eigenthings/loss_fns/standard.py ran MIT (permissive) · c6d693d00d07065a · report fixture: signature criterion:callable/0/? · returned function · level recorded 2026-09-26
total_size hessian_eigenthings/param_utils.py ran MIT (permissive) · 2a6e6bf2f11014cd · report fixture: returned int · level recorded 2026-09-26
compiled_ce_hvp hessian_eigenthings/loss_fns/_fused_ce_hvp.py unverified MIT (permissive) · 14b80a5196e7bbc3 · report
triton_ce_hvp hessian_eigenthings/loss_fns/_fused_ce_hvp.py unverified MIT (permissive) · 48740a084aa48f93 · report

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