Papers › Regularizing Neural Networks via Adversarial Model Perturbation

Regularizing Neural Networks via Adversarial Model Perturbation

10 Oct 2020CVPR 2021 1arXiv:2010.04925archive 2025-07-28

Yaowei Zheng, Richong Zhang, Yongyi Mao

Effective regularization techniques are highly desired in deep learning for alleviating overfitting and improving generalization. This work proposes a new regularization scheme, based on the understanding that the flat local minima of the empirical risk cause the model to generalize better. This scheme is referred to as adversarial model perturbation (AMP), where instead of directly minimizing the empirical risk, an alternative "AMP loss" is minimized via SGD. Specifically, the AMP loss is obtained from the empirical risk by applying the "worst" norm-bounded perturbation on each point in the parameter space. Comparing with most existing regularization schemes, AMP has strong theoretical justifications, in that minimizing the AMP loss can be shown theoretically to favour flat local minima of the empirical risk. Extensive experiments on various modern deep architectures establish AMP as a new state of the art among regularization schemes. Our code is available at https://github.com/hiyouga/AMP-Regularizer.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2010.04925")

Code

Syntology Ran 0 of 12 code samples harvested from 1 repository linked to this paper; 12 have no recorded run.

By repository: official repository: 12 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hiyouga/AMP-Regularizer officialmentioned in papermentioned on GitHubpytorchMIT 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

12 samples harvested; 0 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

12unverified

Licence: 0 of the 12 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 hiyouga/AMP-Regularizer. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

load_data hiyouga/AMP-Regularizer/data_utils.py official repository unverified MIT (permissive) · 23f8ddd9d3036986 · report
preactresnet18 hiyouga/AMP-Regularizer/models/preresnet.py official repository unverified MIT (permissive) · 56f5d1e18818a588 · report
preactresnet34 hiyouga/AMP-Regularizer/models/preresnet.py official repository unverified MIT (permissive) · ad06e17d93d199b1 · report
preactresnet50 hiyouga/AMP-Regularizer/models/preresnet.py official repository unverified MIT (permissive) · 69fa6ac35bf73933 · report
pyramidnet110_270 hiyouga/AMP-Regularizer/models/pyramidnet.py official repository unverified MIT (permissive) · 2e823415fd8892d3 · report
pyramidnet110_48 hiyouga/AMP-Regularizer/models/pyramidnet.py official repository unverified MIT (permissive) · 3becec1c5733895e · report
pyramidnet110_84 hiyouga/AMP-Regularizer/models/pyramidnet.py official repository unverified MIT (permissive) · f4cf5fef0cb3846f · report
vgg11 hiyouga/AMP-Regularizer/models/vgg.py official repository unverified MIT (permissive) · c96e667a110ad914 · report
vgg13 hiyouga/AMP-Regularizer/models/vgg.py official repository unverified MIT (permissive) · a87c587db9bb46e7 · report
vgg16 hiyouga/AMP-Regularizer/models/vgg.py official repository unverified MIT (permissive) · 27be89a48a746a7e · report
wrn28_10 hiyouga/AMP-Regularizer/models/wide_resnet.py official repository unverified MIT (permissive) · fb3b654b466c7bbc · report
wrn28_2 hiyouga/AMP-Regularizer/models/wide_resnet.py official repository unverified MIT (permissive) · aa571c42c4e5cc1c · report

Tasks

Image Classificationmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 PyramidNet + AA (AMP) Percentage correct 98.02 #56 of 265 Archive leaderboard report
Image Classification CIFAR-10 PreActResNet18 (AMP) Percentage correct 96.03 #122 of 265 Archive leaderboard report
Image Classification CIFAR-100 PyramidNet + AA (AMP) Percentage correct 86.64 #51 of 211 Archive leaderboard report
Image Classification CIFAR-100 PreActResNet18 (AMP) Percentage correct 78.49 #137 of 211 Archive leaderboard report
Image Classification SVHN PyramidNet + AA (AMP) Percentage error 1.35 #7 of 62 Archive leaderboard report
Image Classification SVHN PreActResNet18 (AMP) Percentage error 2.30 #33 of 62 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: AMP

AMPAutoAugmentConvolutionCutoutMax PoolingPyramidNetReLUSGD with Momentum

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