SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.06703 · 2023

Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2308.06703.json · badge: /api/ran/2308.06703.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
averyma/opt-robust canonical (classifier label)
classifier basis: census
11 ran · 2 no recorded run
FunctionStatusWhere it lives
L1_projection Ran
ran; our contract draft was wrong, not the code
averyma/opt-robust/autoattack/autopgd_base.py
pointer only (licence: NONE) · get_code("7325c49fd8c6a7d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

PreActResNet18 Ran
ran; our contract draft was wrong, not the code
averyma/opt-robust/models/preact_resnet.py
pointer only (licence: NONE) · get_code("6bc11692e189a289")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
averyma/opt-robust/src/evaluation.py
pointer only (licence: NONE) · get_code("18badd533b52adb3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

check_range_output Ran
ran; our contract draft was wrong, not the code
averyma/opt-robust/autoattack/checks.py
pointer only (licence: NONE); the stored copy get_code serves, from junjieyang97/rgd, is pointer only (licence: LGPL-3.0) · get_code("5d7ff050610414d0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dct Ran
ran; our contract draft was wrong, not the code
averyma/opt-robust/src/utils_freq.py
pointer only (licence: NONE) · get_code("f0531ec5d46051d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

getDCTmatrix Ran
ran, honoured the contract we drafted
averyma/opt-robust/src/utils_freq.py
pointer only (licence: NONE) · get_code("495939172299431d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_default Ran
ran; our contract draft was wrong, not the code
averyma/opt-robust/src/args.py
pointer only (licence: NONE); the stored copy get_code serves, from averyma/model-alignment, is pointer only (licence: NONE) · get_code("dfbe996ba309751d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_optim Ran
ran; our contract draft was wrong, not the code
averyma/opt-robust/src/utils_general.py
pointer only (licence: NONE) · get_code("634dbd17789eb3c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_dataset Ran
ran; our contract draft was wrong, not the code
averyma/opt-robust/src/utils_dataset.py
pointer only (licence: NONE) · get_code("62c890936a7eb164")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rgb2gray Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
averyma/opt-robust/src/utils_freq.py
pointer only (licence: NONE) · get_code("b05531e1744cf65d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

test_gaussian Ran
ran, honoured the contract we drafted
averyma/opt-robust/src/evaluation.py
pointer only (licence: NONE) · get_code("a74d4e0d09a51e6b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

returnTestLoss Not yet run
unverified (harvested, no recorded run)
averyma/opt-robust/src/linear_analysis.py
pointer only (licence: NONE) · get_code("15661e7286adc915")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

test_clean Not yet run
unverified (harvested, no recorded run)
averyma/opt-robust/src/evaluation.py
pointer only (licence: NONE) · get_code("2ba84c242554901e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, averyma/opt-robust when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
accuracy 19 other papers
8 dated earlier, 11 later
1805.08318 (2018-05)
Self-Attention Generative Adversarial Networks
2105.14148 (2021-05)
OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
2110.03006 (2021-10)
Unsupervised Selective Labeling for More Effective Semi-Supervised Learning
and 16 more not named here
L1_projection 8 other papers
5 dated earlier, 3 later · 2 only as an assembly brick
1511.00561 (2015-11)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
2103.01208 (2021-03)
Mind the Box: l 1 -APGD for Sparse Adversarial Attacks on Image Classifiers
2103.14222 (2021-03)
Adversarial Attacks are Reversible with Natural Supervision
and 5 more not named here
check_range_output 1 other paper
1 later
2312.01260 (2023-12)
Rethinking PGD Attack: Is Sign Function Necessary?
get_default 1 other paper
1 later
2311.18495 (2023-11)
Improving Adversarial Transferability via Model Alignment

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Stochastic gradient descent (SGD) and adaptive gradient methods, such as Adam and RMSProp, have been widely used in training deep neural networks. We empirically show that while the difference between the standard generalization performance of models trained using these methods is small, those trained using SGD exhibit far greater robustness under input perturbations. Notably, our investigation demonstrates the presence of irrelevant frequencies in natural datasets, where alterations do not affect models' generalization performance. However, models trained with adaptive methods show sensitivity to these changes, suggesting that their use of irrelevant frequencies can lead to solutions sensitive to perturbations. To better understand this difference, we study the learning dynamics of gradient descent (GD) and sign gradient descent (signGD) on a synthetic dataset that mirrors natural signals. With a three-dimensional input space, the models optimized with GD and signGD have standard risks close to zero but vary in their adversarial risks. Our result shows that linear models' robustness to $\ell_2$-norm bounded changes is inversely proportional to the model parameters' weight norm: a smaller weight norm implies better robustness. In the context of deep learning, our experiments show that SGD-trained neural networks have smaller Lipschitz constants, explaining the better robustness to input perturbations than those trained with adaptive gradient methods.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2308.06703")
get_code_for_paper("2308.06703")
have("2308.06703")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2308.06703.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2308.06703.svg)](https://syntology.ai/paper/2308.06703)

Connect an agent — have() is free.