Papers › Where Do Large Learning Rates Lead Us?

Where Do Large Learning Rates Lead Us?

29 Oct 2024arXiv:2410.22113archive 2025-07-28

Ildus Sadrtdinov, Maxim Kodryan, Eduard Pokonechny, Ekaterina Lobacheva, Dmitry Vetrov

It is generally accepted that starting neural networks training with large learning rates (LRs) improves generalization. Following a line of research devoted to understanding this effect, we conduct an empirical study in a controlled setting focusing on two questions: 1) how large an initial LR is required for obtaining optimal quality, and 2) what are the key differences between models trained with different LRs? We discover that only a narrow range of initial LRs slightly above the convergence threshold lead to optimal results after fine-tuning with a small LR or weight averaging. By studying the local geometry of reached minima, we observe that using LRs from this optimal range allows for the optimization to locate a basin that only contains high-quality minima. Additionally, we show that these initial LRs result in a sparse set of learned features, with a clear focus on those most relevant for the task. In contrast, starting training with too small LRs leads to unstable minima and attempts to learn all features simultaneously, resulting in poor generalization. Conversely, using initial LRs that are too large fails to detect a basin with good solutions and extract meaningful patterns from the data.

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 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 11 ran (8 with no instrument failure; 3 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 2026-09-27 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

isadrtdinov/understanding-large-lrs officialmentioned on GitHubpytorchApache-2.0Syntology: 16 samples, 11 ran (3 instrument-failed) · 5 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.

Code Syntology ran Syntology

16 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
3ran · our draft was wrong
4ran
5unverified

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 isadrtdinov/understanding-large-lrs. “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.

isadrtdinov/understanding-large-lrs official repository 16 samples, 11 ran (3 instrument-failed) · 5 unverified
LogSumExp convolutional_networks/training_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 8cb1d24a1cf29e11 · report fixture: signature x:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-26
Lop convolutional_networks/get_info_funcs.py ran Apache-2.0 (permissive) · 19b54a137a0bbdb7 · report fixture: returned tuple · level recorded 2026-09-27
check_si_name convolutional_networks/get_info.py ran fingerprinted Apache-2.0 (permissive) · d2c03e2aaa143601 · report fixture: signature n:str/0/str, model_name:str/0/str · returned bool · level recorded 2026-09-26
cross_entropy in 92 papers
census: 6 implementations from 8 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
convolutional_networks/custom_training_utils.py ran Apache-2.0 (permissive) · 92278c6d1c2ed4ba · report fixture: signature model:callable/0/?, input:Tensor/2/float, target:Tensor/1/int, reduction:str/0/str · returned tuple · level recorded 2026-09-26
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
convolutional_networks/training_utils.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · cdc64e98aaf2dd54 · report fixture: signature lst:list/1/Tensor · returned Tensor · level recorded, date not recorded
get_grads in 13 papers synthetic_example/model.py ran · honoured contract Apache-2.0 (permissive) · 84a8ef25008d233d · report fixture: signature model:callable/0/? · returned Tensor · level recorded 2026-09-26
get_weights in 34 papers synthetic_example/model.py ran · honoured contract Apache-2.0 (permissive) · 79a3e75a15ed94dd · report fixture: signature model:callable/0/? · returned Tensor · level recorded 2026-09-26
interpolate_state_dicts convolutional_networks/custom_training_utils.py ran Apache-2.0 (permissive) · 6d9487d53006a554 · report fixture: signature model_A_state_dict:dict/0/?, model_B_state_dict:dict/0/?, t:float/0/float · returned OrderedDict · level recorded 2026-09-26
load_state_dict_from_swa_to_usual convolutional_networks/custom_training_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 01063d5c587678c2 · report fixture: signature path:str/0/str · returned OrderedDict · level recorded 2026-09-26
num_params in 7 papers synthetic_example/model.py ran · honoured contract Apache-2.0 (permissive) · d28ce1ac93c376f2 · report fixture: returned int · level recorded 2026-09-27
unflatten_like in 7 papers convolutional_networks/get_info_funcs.py ran · our draft was wrong Apache-2.0 (permissive) · 6d8daee3396e21d5 · report fixture: signature vector:Tensor/1/float, likeTensorList:list/1/Tensor · returned list · level recorded 2026-09-22
Rop in 5 papers convolutional_networks/get_info_funcs.py unverified Apache-2.0 (permissive) · 8bc49ef2a0810046 · report
get_model_extra convolutional_networks/nb_utils.py unverified Apache-2.0 (permissive) · 157cf0b88320c24e · report
get_model_str convolutional_networks/nb_utils.py unverified Apache-2.0 (permissive) · c415f0e6392ad2af · report
svhn_loaders in 5 papers convolutional_networks/data.py unverified Apache-2.0 (permissive) · 182de3ac9284f86e · report
unflatten_like in 7 papers convolutional_networks/training_utils.py unverified Apache-2.0 (permissive) · 2da33912415648f3 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FocusSET

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