Papers › Cyclical Learning Rates for Training Neural Networks

Cyclical Learning Rates for Training Neural Networks

3 Jun 2015arXiv:1506.01186archive 2025-07-28

Leslie N. Smith

It is known that the learning rate is the most important hyper-parameter to tune for training deep neural networks. This paper describes a new method for setting the learning rate, named cyclical learning rates, which practically eliminates the need to experimentally find the best values and schedule for the global learning rates. Instead of monotonically decreasing the learning rate, this method lets the learning rate cyclically vary between reasonable boundary values. Training with cyclical learning rates instead of fixed values achieves improved classification accuracy without a need to tune and often in fewer iterations. This paper also describes a simple way to estimate "reasonable bounds" -- linearly increasing the learning rate of the network for a few epochs. In addition, cyclical learning rates are demonstrated on the CIFAR-10 and CIFAR-100 datasets with ResNets, Stochastic Depth networks, and DenseNets, and the ImageNet dataset with the AlexNet and GoogLeNet architectures. These are practical tools for everyone who trains neural networks.

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

The archive's official repository (bckenstler/CLR) was not harvested; the 15 samples below come from 3 community repositories, and 2 more are identical to code Syntology harvested from another paper's repository.

Syntology 17 code samples: 15 from 3 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 17: 15 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; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 3 repositories, 13 ran (12 with no instrument failure; 1 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 9 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. 2 of the 15 samples that ran have no recorded date.

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

bckenstler/CLR officialmentioned in papermentioned on GitHubtfMITSyntology: not harvested report
AlexMGitHub/Checkers-MCTS mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate,... (arXiv:1803.09820; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
GPUPhobia/vocal-mask mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Decoupled Weight Decay Regularization (arXiv:1711.05101; that paper's own run record: 18 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 3 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified) and End-to-end music source separation: is it possible in the waveform domain? (arXiv:1810.12187; 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
GorillaBus/urban-audio-classifier mentioned on GitHubtfLGPL-3.0Syntology: not harvested report
JavClaude/Cyclical-Learning-Rate mentioned on GitHubSyntology: not harvested report
JitindraFartiyal/Object-Detection mentioned on GitHubpytorchSyntology: not harvested report
Manas2909/Learning-Keras mentioned on GitHubtfSyntology: not harvested report
MichaelNasello/nnFromScratch mentioned on GitHubtfSyntology: not harvested report
Miltos-90/UNet_Biomedical_Image_Segmentation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
Niteeshaballa/fastai-practice mentioned on GitHubSyntology: not harvested report
SevenZhan/Pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SGDR: Stochastic Gradient Descent with Warm Restarts (arXiv:1608.03983; that paper's own run record: 16 ran (of which 7 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
WittmannF/LRFinder mentioned on GitHubSyntology: not harvested report
atnlp/reproduced-ml-papers mentioned on GitHubApache-2.0Syntology: not harvested report
benihime91/one_cycle_lr-tensorflow mentioned on GitHubtfSyntology: not harvested report
benihime91/tensorflow-on-steroids mentioned on GitHubtfSyntology: not harvested report
binmishr/Cyclical-learning-rate-with-R-and-Keras mentioned on GitHubtfSyntology: not harvested report
brianmanderson/Cyclical_Learning_Rate mentioned on GitHubtfMITSyntology: not harvested report
chandansharma02/Deep_Learning mentioned on GitHubpytorchSyntology: not harvested report
coxy1989/clr mentioned on GitHubpytorchSyntology: not harvested report
datalass1/fastai mentioned on GitHubtfSyntology: not harvested report
davidtvs/pytorch-lr-finder mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
delzac/cntk-clr mentioned on GitHubSyntology: not harvested report
erasromani/behavior-cloning mentioned on GitHubpytorchSyntology: not harvested report
gregtozzi/deep_learning_celnav mentioned on GitHubtfSyntology: not harvested report
gurucharanmk/PyTorch_CircularLearningRate mentioned on GitHubpytorchMITSyntology: not harvested report
gurucharanmk/PyTorch_LearningRateFinder mentioned on GitHubpytorchMITSyntology: not harvested report
gurucharanmk/PyTorch_OneCyclePolicyScheduler mentioned on GitHubpytorchMITSyntology: not harvested report
hamiddimyati/dd2424-deep-learning mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification (arXiv:1502.01852; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
haritha91/1cycle-Policy-Experiment mentioned on GitHubpytorchSyntology: not harvested report
jae1213/CyclicalLR_SGDR mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SGDR: Stochastic Gradient Descent with Warm Restarts (arXiv:1608.03983; that paper's own run record: 16 ran (of which 7 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
josequinonez/SkinCancerClassification mentioned on GitHubpytorchMITSyntology: not harvested report
karthikRavichandran/LR_exploration_tf mentioned on GitHubtfSyntology: not harvested report
leona-ha/Skin-Screening_Web-App mentioned on GitHubtfSyntology: not harvested report
lnsmith54/exploring-loss mentioned on GitHubcaffe2GPL-3.0Syntology: not harvested report
lnsmith54/super-convergence mentioned on GitHubcaffe2Syntology: not harvested report
locuslab/fast_adversarial mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fast is better than free: Revisiting adversarial training (arXiv:2001.03994; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 2 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
lrsoenksen/LRFinder mentioned on GitHubtfSyntology: not harvested report
m-romanenko/cycliclr mentioned on GitHubtfSyntology: not harvested report
maikherbig/AIDeveloper mentioned on GitHubtfBSD-2-ClauseSyntology: 13 samples, 11 ran (0 instrument-failed) · 2 unverified report
mhmoodlan/cyclic-learning-rate mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
minhncedutw/prac-keras-cyclical-lr mentioned on GitHubMITSyntology: not harvested report
mpyrozhok/adamwr mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Decoupled Weight Decay Regularization (arXiv:1711.05101; that paper's own run record: 18 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 3 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
nachiket273/One_Cycle_Policy mentioned on GitHubpytorchSyntology: not harvested report
nupam/keras-callbacks mentioned on GitHubtfMITSyntology: not harvested report
simon0987/Fast_FGSM mentioned on GitHubpytorchSyntology: not harvested report
suhas1999/Flip-kart-grid-challenge mentioned on GitHubpytorchMITSyntology: not harvested report
surmenok/keras_lr_finder mentioned on GitHubMITSyntology: not harvested report
valerkabvv/test_tasks mentioned on GitHubpytorchSyntology: not harvested report
yell/kaggle-camera mentioned on GitHubpytorchMITSyntology: not harvested report
ywu94/Code-Notes mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-Sample Dropout for Accelerated Training and Better Generalization (arXiv:1905.09788; that paper's own run record: 7 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; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific-2/code-4 mindsporeSyntology: not harvested report
MindSpore-scientific-2/code-9 mindsporeSyntology: 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.

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

17 samples harvested: 15 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; 3 where Syntology's instrument failed) · 2 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.

3ran · our draft was wrong
12ran
2unverified

Licence: 2 of the 17 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 3 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. 2 samples are listed last, in a group without a repository. “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.

davidtvs/pytorch-lr-finder community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
resnet20 in 42 papers examples/cifar10_resnet.py ran · our draft was wrong MIT (permissive) · e5d7185b6cba3126 · report fixture: signature num_classes:int/0/int, ch_width:int/0/int · returned Cifar10ResNet · level recorded 2026-09-22
maikherbig/AIDeveloper community (archive-listed) 13 samples, 11 ran (0 instrument-failed) · 2 unverified
Example_sequential_api AIDeveloper/model_zoo.py ran BSD-2-Clause (permissive) · cb1b3c9d80104afe · report fixture: signature in_dim:int/0/int, channels:int/0/int, out_dim:int/0/int · returned Sequential · level recorded 2026-09-26
get_default_dict AIDeveloper/aid_start.py ran BSD-2-Clause (permissive) · 0adbffc117bfd132 · report fixture: signature dir_settings:str/0/str · returned dict · level recorded 2026-09-26
get_metrics_strings AIDeveloper/aid_dl.py ran BSD-2-Clause (permissive) · f946f37e1b43a15d · report fixture: signature model_metrics:list/1/str, nr_classes:int/0/int · returned list · level recorded 2026-09-26
get_metrics_tensors AIDeveloper/aid_dl.py ran fingerprinted BSD-2-Clause (permissive) · d00620593ea5d2df · report fixture: signature metrics:list/1/str, nr_classes:int/0/int · returned list · level recorded 2026-09-26
hashfile AIDeveloper/aid_bin.py ran BSD-2-Clause (permissive) · 45a9c41a6b24a718 · report fixture: signature fname:str/0/str, blocksize:int/0/int, count:int/0/int, constructor:callable/0/?, hasher_class:NoneType/0/? · returned str · level recorded 2026-09-26
image_adjust_channels AIDeveloper/aid_img.py ran BSD-2-Clause (permissive) · cf5cbe4cbc370df8 · report fixture: signature images:ndarray/4/int, target_channels:int/0/int · returned ndarray · level recorded 2026-09-26
model_change_trainability AIDeveloper/aid_dl.py ran BSD-2-Clause (permissive) · cd3acc6cca5ab016 · report fixture: signature model_keras:callable/0/?, trainable_new:list/1/bool, model_metrics:list/1/str, out_dim:int/0/int, loss_:str/0/str, optimizer_:dict/0/?, learning_rate_:float/0/float · returned str · level recorded 2026-09-26
obj2bytes AIDeveloper/aid_bin.py ran BSD-2-Clause (permissive) · bf5d386d1b0b6ab0 · report fixture: signature obj:str/0/str · returned bytes · level recorded 2026-09-26
pad_arguments_np2cv AIDeveloper/aid_img.py ran BSD-2-Clause (permissive) · 7ee2ab117ac91fd6 · report fixture: signature padding_mode:str/0/str · returned str · level recorded 2026-09-26
splitall AIDeveloper/aid_bin.py ran fingerprinted BSD-2-Clause (permissive) · 8b4838063b92e952 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-26
zoom_arguments_scipy2cv AIDeveloper/aid_img.py ran fingerprinted BSD-2-Clause (permissive) · 6cf1a30f40bacfe8 · report fixture: signature zoom_factor:float/0/float, zoom_interpol_method:int/0/int · returned str · level recorded 2026-09-26
Example_functional_api AIDeveloper/model_zoo.py unverified BSD-2-Clause (permissive) · 60d8872644d31774 · report
partial_trainability AIDeveloper/partial_trainability.py unverified BSD-2-Clause (permissive) · 9f17041c328ef059 · report
mhmoodlan/cyclic-learning-rate community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
cyclic_learning_rate clr.py ran MIT (permissive) · a20814d7bfa74719 · report fixture: signature global_step:ResourceVariable/0/int, learning_rate:float/0/float, max_lr:float/0/float, step_size:float/0/float, gamma:float/0/float, mode:str/0/str, name:str/0/str · returned function · level recorded 2026-09-26
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
conv1x1 in 691 papers repository not located ran · our draft was wrong licence of this copy not recorded · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers repository not located ran · our draft was wrong licence of this copy not recorded · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAuxiliary ClassifierAverage PoolingConvolutionDense ConnectionsDropoutGoogLeNetGrouped ConvolutionInception ModuleLocal Response NormalizationMax PoolingReLUSoftmax

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