Papers › Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks

Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks

27 May 2019arXiv:1905.11286archive 2025-07-28

Boris Ginsburg, Patrice Castonguay, Oleksii Hrinchuk, Oleksii Kuchaiev, Vitaly Lavrukhin, Ryan Leary, Jason Li, Huyen Nguyen, Yang Zhang, Jonathan M. Cohen

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation, and language modeling, it performs on par or better than well tuned SGD with momentum and Adam or AdamW. Additionally, NovoGrad (1) is robust to the choice of learning rate and weight initialization, (2) works well in a large batch setting, and (3) has two times smaller memory footprint than Adam.

PaperPDFCodeCode 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

Syntology 16 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: named in the paper: 5 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 11 samples from 1 repository, 8 ran (7 with no instrument failure; 1 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

NVIDIA/OpenSeq2Seq mentioned in papertfApache-2.0Syntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
Edresson/VoiceSplit mentioned on GitHubpytorchApache-2.0Syntology: 11 samples, 8 ran (1 instrument-failed) · 3 unverified report
convergence-lab/novograd mentioned on GitHubpytorchApache-2.0Syntology: not harvested 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

16 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 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.

1ran · our draft was wrong
12ran
3unverified

Licence: 1 of the 16 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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. 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.

NVIDIA/OpenSeq2Seq named in the paper 5 samples, 5 ran (0 instrument-failed) · 0 unverified
levenshtein in 8 papers external_lm_rescore/process_beam_dump.py ran fingerprinted Apache-2.0 (permissive) · 3ca5033f79170e1d · report fixture: signature a:str/0/str, b:str/0/str · returned int · level recorded 2026-09-24
load_test_sample ctc_decoder_with_lm/ctc-test.py ran Apache-2.0 (permissive) · 208ca2fc2f2bfbce · report fixture: signature pickle_file:str/0/str · returned tuple · level recorded 2026-09-24
load_vocab in 107 papers ctc_decoder_with_lm/ctc-test.py ran Apache-2.0 (permissive) · 00c6b131afd785b5 · report fixture: signature vocab_file:str/0/str · returned list · level recorded 2026-09-24
score_fun_linear external_lm_rescore/process_beam_dump.py ran fingerprinted Apache-2.0 (permissive) · fe91957d004bddae · report fixture: signature s1:Tensor/2/float, s2:Tensor/2/float, s3:Tensor/2/float, s4:Tensor/2/float · returned Tensor · level recorded 2026-09-24
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
frame_asr.py ran fingerprinted Apache-2.0 (permissive) · 758f37e8c4f07d0f · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-24
Edresson/VoiceSplit community (archive-listed) 11 samples, 8 ran (1 instrument-failed) · 3 unverified
dynamic_range_compression in 31 papers utils/audio.py ran fingerprinted Apache-2.0 (permissive) · e2be51dbbe1b0417 · report fixture: signature x:Tensor/2/float, C:int/0/int, clip_val:float/0/float · returned Tensor · level recorded 2026-09-24
dynamic_range_decompression in 15 papers utils/audio.py ran fingerprinted Apache-2.0 (permissive) · f2c495798df6e4e4 · report fixture: signature x:Tensor/2/float, C:int/0/int · returned Tensor · level recorded 2026-09-24
eval_dataloader utils/dataset.py ran Apache-2.0 (permissive) · 37bbc4307e40fc3d · report fixture: signature c:Config/0/?, ap:AudioProcessor/0/? · returned DataLoader · level recorded 2026-09-24
formatter in 6 papers generator_paper.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 9563ca1187f4def1 · report fixture: signature dir_:str/0/str, form:str/0/str, num:int/0/int · returned str · level recorded 2026-09-22
get_audios_with_random_amp utils/generic_utils.py ran fingerprinted Apache-2.0 (permissive) · 2f44eccb0ea1dddd · report fixture: signature emb_audio:ndarray/2/float, clean_audio:ndarray/2/float, interference:ndarray/2/float, noise_audio:ndarray/2/float · returned tuple · level recorded 2026-09-24
get_mask in 119 papers
census: 9 implementations from 10 papers, 9 distinct outputs across 7 buckets, one shared input per bucket
utils/generic_utils.py ran Apache-2.0 (permissive) · b490372d6caf2e08 · report fixture: signature source:Tensor/3/float, source_lengths:Tensor/1/int · returned Tensor · level recorded 2026-09-24
glob_re_to_filename utils/generic_utils.py ran Apache-2.0 (permissive) · 8b74825f106b92de · report fixture: signature dire:str/0/str, glob:str/0/str, num:int/0/int, sub:bool/0/bool · returned str · level recorded 2026-09-24
train_dataloader utils/dataset.py ran Apache-2.0 (permissive) · b4d4be1b39e495ba · report fixture: signature c:Config/0/?, ap:AudioProcessor/0/? · returned DataLoader · level recorded 2026-09-24
fig2np utils/tensorboard.py unverified Apache-2.0 (permissive) · 63cdde3c993f3ca1 · report
plot_spectrogram_to_numpy in 8 papers utils/tensorboard.py unverified Apache-2.0 (permissive) · c34124e879d7f774 · report
test_dataloader utils/dataset.py unverified Apache-2.0 (permissive) · 433047dab631b9ad · report

Tasks

General ClassificationLanguage ModelingStochastic OptimizationTranslationimage-classificationspeech-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAdamWSGDSGD 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