Papers › Adam: A Method for Stochastic Optimization

Adam: A Method for Stochastic Optimization

22 Dec 2014arXiv:1412.6980archive 2025-07-28

Diederik P. Kingma, Jimmy Ba

We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.

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.

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

Code

Syntology 37 code samples harvested from 14 repositories linked to this paper: 27 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 4 honoured, 2 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 37 samples from 14 repositories, 27 ran (23 with no instrument failure; 4 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 13 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.

87 repositories listed; official and paper-mentioned ones first.

201419/Optimizer-PyTorch mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On the Variance of the Adaptive Learning Rate and Beyond (arXiv:1908.03265; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
AlbertUW807/DLNN-Algo mentioned on GitHubSyntology: not harvested report
Anunay1234/Sentiment-Analysis-using-LSTM mentioned on GitHubSyntology: not harvested report
BarbaAlGhul/recommender-system-thesis mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to In Defense of the Triplet Loss for Person Re-Identification (arXiv:1703.07737; that paper's own run record: 39 ran (of which 0 constructed an object rather than computing a result; 37 with no instrument failure: 3 honoured, 0 violated, 34 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
Cheese-5040/OCT-Scan-Segmentation mentioned on GitHubtfSyntology: not harvested report
ChengBinJin/Adam-Analysis-TensorFlow mentioned on GitHubtfSyntology: not harvested report
DChaushev/Age-Gender-Recognition mentioned on GitHubtfSyntology: not harvested report
DylanMuir/fmin_adam mentioned on GitHubSyntology: not harvested report
Fabrolly/DeepLearning-Experiment-on-Taiwan-Payaments-Information mentioned on GitHubSyntology: not harvested report
GLambard/AdamW_Keras mentioned on GitHubtfSyntology: not harvested report
JiaYunSong/Gan-for-Gem-Generation mentioned on GitHubpaddleSyntology: not harvested report
KhalilJDamouni/RMSGD_Pretest mentioned on GitHubpytorchMITSyntology: 11 samples, 7 ran (2 instrument-failed) · 4 unverified report
MichaelKonobeev/adashift mentioned on GitHubtfMITSyntology: not harvested report
Orchidaceae/AI_palette_recommendation mentioned on GitHubtfSyntology: not harvested report
Rohit-ChoudharyGit/Train_Fashion_MNIST mentioned on GitHubtfSyntology: not harvested report
SamuelMarks/doctrans mentioned on GitHubtfApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
Sj-Amani/Practical_Behavioral_Cloning mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Songlielie/DKT-Plus mentioned on GitHubtfSyntology: not harvested report
Taichi-Yoshikawa/NeuralNetwork mentioned on GitHubMITSyntology: not harvested report
TimRoith/BregmanLearning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Bregman Learning Framework for Sparse Neural Networks (arXiv:2105.04319; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
VAZaytsev/QITE mentioned on GitHubSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Xinyi6/CIFAR10-CNN-by-Keras mentioned on GitHubpytorchSyntology: not harvested report
ZMpursue/Anime_avatar_generation mentioned on GitHubpaddleSyntology: not harvested report
alisterta/Persian-text-to-speech mentioned on GitHubtfSyntology: not harvested report
alpaficia/MOSEAC_Limo mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Soft Actor-Critic Algorithms and Applications (arXiv:1812.05905; that paper's own run record: 38 ran (of which 0 constructed an object rather than computing a result; 35 with no instrument failure: 4 honoured, 1 violated, 30 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
andreblumenau/Contemporary-Neural-Network mentioned on GitHubSyntology: not harvested report
arampacha/clip-rsicd mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Adafactor: Adaptive Learning Rates with Sublinear Memory Cost (arXiv:1804.04235; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
bsvineethiitg/adams mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Exploiting Uncertainty of Loss Landscape for Stochastic Optimization (arXiv:1905.13200; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
changhuixu/LSTM-sentiment-analysis mentioned on GitHubSyntology: not harvested report
chuiyunjun/projectCSC413 mentioned on GitHubSyntology: not harvested report
cjc77/gaussian_processes_final_project mentioned on GitHubSyntology: not harvested report
crowsonkb/esgd mentioned on GitHubpytorchMITSyntology: not harvested report
data-llectual/ml-dna mentioned on GitHubtfSyntology: not harvested report
hoanghuy89/CNN-from-first-principle mentioned on GitHubpytorchSyntology: not harvested report
hsvgbkhgbv/TACTHMC mentioned on GitHubpytorchSyntology: not harvested report
huybik/CNN-from-first-principle mentioned on GitHubpytorchSyntology: not harvested report
hydrogo/rainnet mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (arXiv:1511.00561; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
ilguyi/optimizers.numpy mentioned on GitHubtfApache-2.0Syntology: not harvested report
jangsoopark/IDN-TensorFlow mentioned on GitHubtfSyntology: not harvested report
jliphard/DeepEvolve mentioned on GitHubNOASSERTIONSyntology: not harvested report
joseluis1061/neuralnilm mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural NILM: Deep Neural Networks Applied to Energy Disaggregation (arXiv:1507.06594; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
jpjuvo/64-3D-RaSGAN mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improved Adversarial Systems for 3D Object Generation and Reconstruction (arXiv:1707.09557; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
kapilnchauhan77/Disfluency-Detection mentioned on GitHubSyntology: not harvested report
ken-power/CVND-FacialKeypointDetection mentioned on GitHubpytorchSyntology: not harvested report
kkrajczar/DSGeneric mentioned on GitHubSyntology: not harvested report
mahdihosseini/AdaS mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
mirzaevinom/data_science_bowl_2018 mentioned on GitHubtfSyntology: not harvested report
mohamedameen93/German-Traffic-Sign-Classification-Using-TensorFlow mentioned on GitHubtfMITSyntology: not harvested report
navdeepkumar12/Tic mentioned on GitHubSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
nnaisense/pgpelib mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
nyatadecocoa/Machine_Learning_Midterm_Assignment_2019 mentioned on GitHubtfSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
offscale/cdd-python mentioned on GitHubtfApache-2.0Syntology: not harvested report
rahulsonone1234/Traffic-Sign-Recognition mentioned on GitHubtfGPL-3.0Syntology: not harvested report
rahulsonone1234/traffic-sign- mentioned on GitHubtfGPL-3.0Syntology: not harvested report
rokkian/adam_implementation mentioned on GitHubSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
safakkbilici/Academic-Paper-Title-Recommendation mentioned on GitHubSyntology: not harvested report
sayred1/CNN mentioned on GitHubtfSyntology: not harvested report
sbieringer/adammcmc mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
sbieringer/csmala mentioned on GitHubpytorchSyntology: not harvested report
sdyy6211/plant-segmentation mentioned on GitHubpytorchSyntology: not harvested report
shinyingl/SelfDrivingCar-P3 mentioned on GitHubSyntology: not harvested report
shmanubhav/LunarLander-ApproxQLearning mentioned on GitHubGPL-3.0Syntology: not harvested report
siddarth-c/FedGMA mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Communication-Efficient Learning of Deep Networks from Decentralized Data (arXiv:1602.05629; that paper's own run record: 47 ran (of which 17 constructed an object rather than computing a result; 27 with no instrument failure: 2 honoured, 0 violated, 25 with no contract checked; 20 where Syntology's instrument failed) · 30 unverified); nothing checks that they implement this paper's method. report
sisl/MultiAgentVariationalOcclusionInference mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Discrete Representation Learning (arXiv:1711.00937; that paper's own run record: 64 ran (of which 35 constructed an object rather than computing a result; 60 with no instrument failure: 0 honoured, 0 violated, 60 with no contract checked; 4 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
skanda99/Simple-Neural-Networks mentioned on GitHubtfSyntology: not harvested report
suzyi/optimization mentioned on GitHubSyntology: not harvested report
tomkimpson/ml4l mentioned on GitHubtfMITSyntology: 3 samples, 0 ran · 3 unverified report
vanyle/vlearn mentioned on GitHubtfSyntology: not harvested report
vedpatel49/Neural-Style-Transfer mentioned on GitHubpytorchSyntology: not harvested report
xhlulu/arxiv-assistant mentioned on GitHubSyntology: not harvested report
ylytkin/backpropagation mentioned on GitHubSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
zhangtj1996/lookahead-sgd-adam-rmsprop- mentioned on GitHubtfSyntology: not harvested report
zhenxun-zhuang/SGD-Exponential-Stepsize mentioned on GitHubpytorchSyntology: not harvested report
zhuchen03/maxva mentioned on GitHubpytorchSyntology: not harvested report
zhuchen03/mva mentioned on GitHubpytorchSyntology: not harvested report
MalayAgr/DeepNeuralNetwork-Scratch tfMITSyntology: not harvested report
MaximeVandegar/Papers-in-100-Lines-of-Code pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
MindCode-4/code-11 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Entropy Law: The Story Behind Data Compression and LLM Performance (arXiv:2407.06645; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-6 mindsporeSyntology: not harvested report
MindSpore-scientific/code-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Coneheads: Hierarchy Aware Attention (arXiv:2306.00392; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
kingkingofall/MindSpore-Adam mindsporeSyntology: not harvested report
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: 1 sample, 0 ran · 1 unverified report
lpz555/mindspore-Adam mindsporeSyntology: not harvested report
vpj/jax_transformer jaxSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 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

37 samples harvested: 27 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 4 honoured, 2 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 10 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.

4ran · honoured contract
2ran · violated contract
2ran · our draft was wrong
2ran; the contract check could not run
17ran
10unverified

Licence: 8 of the 37 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 14 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. 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.

KhalilJDamouni/RMSGD_Pretest community (archive-listed) 11 samples, 7 ran (2 instrument-failed) · 4 unverified
EVBMF src/adas/VBMF.py ran MIT (permissive) · 8afdc607e63b281b · report fixture: signature Y:Tensor/2/float, sigma2:NoneType/0/?, H:NoneType/0/? · returned tuple · level recorded 2026-09-26
VBMF src/adas/VBMF.py ran · our draft was wrong fingerprinted MIT (permissive) · 0f7078f4c86b344a · report fixture: signature Y:ndarray/2/float, cacb:float/0/float, sigma2:NoneType/0/?, H:NoneType/0/? · returned tuple · level recorded 2026-09-22
VBMF src/adas/matrix_factorization.py ran MIT (permissive) · 8f58597b290faee4 · report fixture: signature Y:ndarray/2/float, cacb:float/0/float, sigma2:NoneType/0/?, H:NoneType/0/? · returned tuple · level recorded 2026-09-26
VBsigma2 src/adas/VBMF.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 9e8ce2d162e22cdd · report fixture: signature sigma2:float/0/float, L:int/0/int, M:int/0/int, cacb:float/0/float, s:ndarray/1/float, residual:float/0/float · returned float64 · level recorded 2026-09-22
alexnet in 42 papers src/adas/models/alexnet.py ran MIT (permissive) · cd7d9260519b0c88 · report fixture: signature pretrained:bool/0/bool, progress:bool/0/bool · returned AlexNet · level recorded 2026-09-26
safe_float_cast src/adas/utils.py ran fingerprinted MIT (permissive) · 9a5925e41635d417 · report fixture: signature str_number:str/0/str · returned float · level recorded 2026-09-26
smart_string_to_float src/adas/utils.py ran MIT (permissive) · 0a32bb4b38232251 · report fixture: signature string:str/0/str, e:str/0/str · returned float · level recorded 2026-09-26
get_data in 223 papers src/adas/data.py unverified MIT (permissive) · ab7b976a4eb5340d · report
load_meta_file src/adas/datasets.py unverified MIT (permissive) · 5e1f354096a8c5bc · report
parse_devkit_archive src/adas/datasets.py unverified MIT (permissive) · 6257f483693ebe01 · report
pstats_to_dict src/adas/utils.py unverified MIT (permissive) · fd7ae3f51b2d34cd · report
SamuelMarks/doctrans community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
clear_annotation cdd/compound/doctrans_utils.py ran Apache-2.0 (permissive) · d05c0d4ad3893add · report fixture: signature node:AnnAssign/0/? · returned AnnAssign · level recorded 2026-09-26
has_type_annotations cdd/compound/doctrans_utils.py ran Apache-2.0 (permissive) · b8d84bad5cfe2f9c · report fixture: signature node:FunctionDef/0/? · returned bool · level recorded 2026-09-26
Sj-Amani/Practical_Behavioral_Cloning community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
moving_average in 46 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
left_right_driving_data_preprocessing.py ran fingerprinted MIT (permissive) · 755b233b6180c3d0 · report fixture: signature a:ndarray/1/float, n:int/0/int · returned ndarray · level recorded 2026-09-26
VAZaytsev/QITE community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Adam_cls optimizers.py ran no licence file found · pointer only · 6f648e6ff626dfd5 · report fixture: returned Adam_cls · level recorded 2026-09-22
mahdihosseini/AdaS community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
EVBMF src/rmsgd/matrix_factorization.py ran MIT (permissive) · 35275a9e3c1edf4f · report fixture: signature Y:Tensor/2/float, sigma2:NoneType/0/?, H:NoneType/0/? · returned tuple · level recorded 2026-09-26
EVBsigma2 src/rmsgd/matrix_factorization.py ran · violated contract fingerprinted MIT (permissive) · e2f77eaf75568aa2 · report fixture: signature sigma2:float/0/float, L:int/0/int, M:int/0/int, s:ndarray/1/float, residual:float/0/float, xubar:float/0/float · returned float64 · level recorded 2026-09-22
phi0 src/rmsgd/matrix_factorization.py ran · violated contract fingerprinted MIT (permissive) · 2760d409b48cf23f · report fixture: signature x:ndarray/1/float · returned ndarray · level recorded 2026-09-22
navdeepkumar12/Tic community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
adam in 11 papers nn.py ran fingerprinted no licence file found · pointer only · d617942446009de2 · report fixture: signature dw:ndarray/2/float · returned ndarray · level recorded 2026-09-24
optimizer in 7 papers nn.py ran no licence file found · pointer only · 77da68eb2be45988 · report fixture: returned optimizer · level recorded 2026-09-22
nnaisense/pgpelib community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Adam in 7 papers pgpelib/optimizers.py ran BSD-3-Clause (permissive) · 7f2c925da971c0b5 · report fixture: returned Adam · level recorded 2026-09-22
Optimizer in 18 papers pgpelib/optimizers.py ran BSD-3-Clause (permissive) · 2601595a91035c3b · report fixture: returned Optimizer · level recorded 2026-09-22
positive_float pgpelib/optimizers.py ran · honoured contract fingerprinted BSD-3-Clause (permissive) · 2425339890ade98d · report fixture: signature x:float/0/float · returned float · level recorded 2026-09-22
positive_int in 6 papers pgpelib/optimizers.py ran · honoured contract fingerprinted BSD-3-Clause (permissive) · 3c047cbc5f859f9b · report fixture: signature x:int/0/int · returned int · level recorded 2026-09-22
nyatadecocoa/Machine_Learning_Midterm_Assignment_2019 community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
st_ops Problem7/adam.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 62c36ccd5072fcd8 · report fixture: signature mu:ndarray/1/float, q:float/0/float · returned ndarray · level recorded 2026-09-22
optimize in 11 papers Problem7/adam.py unverified no licence file found · pointer only · c5c5da8da7132910 · report
rokkian/adam_implementation community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
adam in 11 papers adam_implementation.py ran · our draft was wrong Apache-2.0 (permissive) · da1304a720259f4d · report fixture: signature objective:callable/0/?, derivative:callable/0/?, bounds:ndarray/2/float, n_iter:int/0/int, alpha:float/0/float, beta1:float/0/float, beta2:float/0/float, eps:float/0/float · returned list · level recorded 2026-09-22
derivative adam_implementation.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 4618e61672a36671 · report fixture: signature x:float/0/float, y:float/0/float · returned ndarray · level recorded 2026-09-22
objective in 14 papers adam_implementation.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · f6c61d4de559ffe9 · report fixture: signature x:float/0/float, y:float/0/float · returned float · level recorded 2026-09-22
tomkimpson/ml4l community (archive-listed) 3 samples, 0 ran · 3 unverified
process_MODIS_file legacy/legacy_scripts/join_MODIS_with_ERA_V2.py unverified MIT (permissive) · 1a88d05a828e9b9c · report
select_correct_MODIS_file legacy/legacy_scripts/join_MODIS_with_ERA_V2.py unverified MIT (permissive) · a3a5ccc0ea8274ee · report
train_NN legacy/legacy_scripts/feature_importance.py unverified MIT (permissive) · 540ea376e18a8af6 · report
ylytkin/backpropagation community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
NeuralNetwork in 7 papers neural_network/neural_network.py ran no licence file found · pointer only · 7ce4d43450d6e037 · report fixture: returned NeuralNetwork · level recorded 2026-09-22
MaximeVandegar/Papers-in-100-Lines-of-Code community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Adam in 7 papers Adam_a_Method_For_Stochastic_Optimization/adam.py ran MIT (permissive) · cbb1359e9a11e474 · report fixture: returned Adam · level recorded 2026-09-22
labmlai/annotated_deep_learning_paper_implementations community (archive-listed) 1 sample, 0 ran · 1 unverified
Adam in 7 papers labml_nn/optimizers/adam.py unverified MIT (permissive) · 10c32bb6eaf9662a · report
vpj/jax_transformer community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
AdamState transformer.py ran · metamorphic tier: invariant no licence file found · pointer only · 9dfa8e2f09245ff2 · report fixture: returned AdamState · level recorded 2026-09-22
Adam in 7 papers transformer.py unverified no licence file found · pointer only · c48006199ed3e050 · 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. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

9 assemblies on this paper: 9 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

9 sibling assemblies for Adam (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Adam (graph method: Adam). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. Adam entry · level 1 · ran · 7f2c925da971c0b5
  2. Optimizer helper · level 1 · ran · 2601595a91035c3b
  3. positive_float helper · level 1 · ran · honoured contract · 2425339890ade98d
  4. positive_int helper · level 1 · ran · honoured contract · 3c047cbc5f859f9b

harvested Assembly for Adam (graph method: Adam). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 9 siblings

  1. Adam entry · level 0 · unverified · c48006199ed3e050
  2. AdamState helper · level 1 · ran · 9dfa8e2f09245ff2

harvested Assembly for Adam (graph method: Adam). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. adam entry · level 1 · ran · d617942446009de2
  2. optimizer helper · level 1 · ran · 77da68eb2be45988

harvested Assembly for Adam (graph method: Adam). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 9 siblings

  1. Adam entry · level 1 · ran · cbb1359e9a11e474

harvested Assembly for Adam (graph method: Adam). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 9 siblings

  1. NeuralNetwork entry · level 1 · ran · 7ce4d43450d6e037

harvested Assembly for Adam (graph method: Adam). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. optimize entry · level 0 · unverified · c5c5da8da7132910
  2. st_ops helper · level 1 · ran; the contract check could not run (RAISES) · 62c36ccd5072fcd8

harvested Assembly for Adam (graph method: Adam). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 9 siblings

  1. Adam_cls entry · level 1 · ran · 6f648e6ff626dfd5

harvested Assembly for Adam (graph method: Adam). 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. adam entry · level 1 · ran · our draft was wrong · da1304a720259f4d
  2. derivative helper · level 1 · ran · honoured contract · 4618e61672a36671
  3. objective helper · level 1 · ran · honoured contract · f6c61d4de559ffe9

harvested Assembly for Adam (graph method: Adam). 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 9 siblings

  1. Adam entry · level 0 · unverified · 10c32bb6eaf9662a
  2. GenericAdaptiveOptimizer helper · level 1 · ran · 15bc730db57a3642
  3. WeightDecay helper · level 1 · ran · ba6a2ba94fbeb5e9

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="1412.6980") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Stochastic Optimization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdaMaxAdam

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