Papers › ADOPT: Modified Adam Can Converge with Any β₂ with the Optimal Rate

ADOPT: Modified Adam Can Converge with Any β₂ with the Optimal Rate

5 Nov 2024arXiv:2411.02853archive 2025-07-28

Shohei Taniguchi, Keno Harada, Gouki Minegishi, Yuta Oshima, Seong Cheol Jeong, Go Nagahara, Tomoshi Iiyama, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo

Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., β₂, in a problem-dependent manner. There have been many attempts to fix the non-convergence (e.g., AMSGrad), but they require an impractical assumption that the gradient noise is uniformly bounded. In this paper, we propose a new adaptive gradient method named ADOPT, which achieves the optimal convergence rate of 𝒪 ( 1 / √(T) ) with any choice of β₂ without depending on the bounded noise assumption. ADOPT addresses the non-convergence issue of Adam by removing the current gradient from the second moment estimate and changing the order of the momentum update and the normalization by the second moment estimate. We also conduct intensive numerical experiments, and verify that our ADOPT achieves superior results compared to Adam and its variants across a wide range of tasks, including image classification, generative modeling, natural language processing, and deep reinforcement learning. The implementation is available at https://github.com/iShohei220/adopt.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2411.02853")

Code

Syntology Ran 4 of 23 code samples harvested from 2 repositories linked to this paper; 19 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 5 samples from 1 repository, 1 ran; found in paper text by Syntology: 18 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ishohei220/adopt officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
huggingface/pytorch-image-models mentioned on GitHubpytorchApache-2.0 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

23 samples harvested; 4 ran; 0 honoured the contract we drafted; 19 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
1ran · fixture could not drive it
1ran
19unverified

Licence: 0 of the 23 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; each sample names its own and says which. “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.

accuracy iShohei220/adopt/imagenet/utils.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 0d95e28fac98427f · report
average_checkpoints iShohei220/adopt/imagenet/utils.py official repository unverified Apache-2.0 (permissive) · 4eca7815147e1708 · report
get_args_parser iShohei220/adopt/imagenet/train_quantization.py official repository unverified Apache-2.0 (permissive) · e36bcfb158ae8f9c · report
get_module iShohei220/adopt/imagenet/presets.py official repository unverified Apache-2.0 (permissive) · b2ea55703711dd12 · report
store_model_weights iShohei220/adopt/imagenet/utils.py official repository unverified Apache-2.0 (permissive) · d92101f375faa8a6 · report
channel_shuffle UiPath/torchvision/torchvision/models/shufflenetv2.py found in paper text by Syntology ran fingerprinted BSD-3-Clause (permissive) · cf7081fc34608ea3 · report
conv1x1 UiPath/torchvision/torchvision/models/resnet.py found in paper text by Syntology ran · our draft was wrong BSD-3-Clause (permissive) · 2a80220dabcb742a · report
conv3x3 UiPath/torchvision/torchvision/models/resnet.py found in paper text by Syntology ran · our draft was wrong BSD-3-Clause (permissive) · 600ff2c45e0de056 · report
alexnet UiPath/torchvision/torchvision/models/alexnet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · 8ccdf1f64321d691 · report
densenet121 UiPath/torchvision/torchvision/models/densenet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · 9eb4b3b03ed7a1c9 · report
densenet161 UiPath/torchvision/torchvision/models/densenet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · e945c7af558f65a9 · report
densenet169 UiPath/torchvision/torchvision/models/densenet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · 858b62a0718acf3c · report
googlenet UiPath/torchvision/torchvision/models/googlenet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · cc86d582f7c75a6d · report
inception_v3 UiPath/torchvision/torchvision/models/inception.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · d5f1aa4870d7ad8b · report
load_meta_file UiPath/torchvision/torchvision/datasets/imagenet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · fd93b84b5a89ac58 · report
mnasnet0_5 UiPath/torchvision/torchvision/models/mnasnet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · 095cb1dfd64f93c1 · report
mnasnet0_75 UiPath/torchvision/torchvision/models/mnasnet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · 561d4224329b8802 · report
mnasnet1_0 UiPath/torchvision/torchvision/models/mnasnet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · 541eb8cf9b978129 · report
mobilenet_v2 UiPath/torchvision/torchvision/models/mobilenetv2.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · 57f30bbef481b9c8 · report
parse_devkit_archive UiPath/torchvision/torchvision/datasets/imagenet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · d523a6fcfaf250c7 · report
resnet18 UiPath/torchvision/torchvision/models/resnet.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · 6af00ec71cf439d8 · report
shufflenet_v2_x0_5 UiPath/torchvision/torchvision/models/shufflenetv2.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · 3edb47a32cd6a773 · report
shufflenet_v2_x1_0 UiPath/torchvision/torchvision/models/shufflenetv2.py found in paper text by Syntology unverified BSD-3-Clause (permissive) · 97931550315207a2 · report

Tasks

Deep Reinforcement LearningImage Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: ADOPT

ADOPTAdam

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