Papers › Improved Analysis of Clipping Algorithms for Non-convex Optimization

Improved Analysis of Clipping Algorithms for Non-convex Optimization

5 Oct 2020NeurIPS 2020 12arXiv:2010.02519archive 2025-07-28

Bohang Zhang, Jikai Jin, Cong Fang, LiWei Wang

Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, show that clipped (stochastic) Gradient Descent (GD) converges faster than vanilla GD/SGD via introducing a new assumption called (L₀, L₁)-smoothness, which characterizes the violent fluctuation of gradients typically encountered in deep neural networks. However, their iteration complexities on the problem-dependent parameters are rather pessimistic, and theoretical justification of clipping combined with other crucial techniques, e.g. momentum acceleration, are still lacking. In this paper, we bridge the gap by presenting a general framework to study the clipping algorithms, which also takes momentum methods into consideration. We provide convergence analysis of the framework in both deterministic and stochastic setting, and demonstrate the tightness of our results by comparing them with existing lower bounds. Our results imply that the efficiency of clipping methods will not degenerate even in highly non-smooth regions of the landscape. Experiments confirm the superiority of clipping-based methods in deep learning tasks.

PaperPDFConference PDFCodeCode 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.

Syntology holds a reference implementation of general framework to study the clipping algorithms, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='general framework to study the clipping algorithms') (how to connect); the free check have('2010.02519') needs no token.

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

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 9 ran (2 with no instrument failure; 7 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. 6 of the 9 samples that ran have no recorded date.

zbh2047/clipping-algorithms officialmentioned in papermentioned on GitHubpytorchSyntology: 12 samples, 9 ran (7 instrument-failed) · 3 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

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 7 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 · honoured contract
3ran · our draft was wrong
4ran; the contract check could not run
1ran
3unverified

Licence: 12 of the 12 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 zbh2047/clipping-algorithms. “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.

zbh2047/clipping-algorithms official repository 12 samples, 9 ran (7 instrument-failed) · 3 unverified
SGDClip algorithm.py ran no licence file found · pointer only · 2f2b5b01c14d1c34 · report fixture: signature paras:list/1/Tensor, state:dict/0/?, group_state:dict/0/?, lr:float/0/float, gamma:float/0/float, momentum:float/0/float · returned NoneType · level recorded 2026-09-24
batchify in 71 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32
main_lstm.py ran · our draft was wrong no licence file found · pointer only · 96d4db57e5c2248f · report fixture: signature data:Tensor/2/float, bsz:int/0/int, args:Args/0/? · returned Tensor · level recorded, date not recorded
get_batch in 82 papers main_lstm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · f1095e1951238c8e · report fixture: signature source:Tensor/1/float, i:int/0/int, args:Namespace/0/?, seq_len:NoneType/0/?, evaluation:bool/0/bool · returned tuple · level recorded, date not recorded
parse_algo main_mnist_cifar.py ran; the contract check could not run (DEP_MISSING) no licence file found · pointer only · 8762f81d32460bc1 · report fixture: signature args:str/0/str, model:callable/0/?, wd:float/0/float, lr:float/0/float, momentum:float/0/float, gamma:float/0/float, b0:float/0/float · returned Algorithm · level recorded, date not recorded
parse_dataset in 8 papers main_mnist_cifar.py ran; the contract check could not run (DEP_MISSING) no licence file found · pointer only · a01e88267842be7f · report fixture: signature args:str/0/str, batch_size:int/0/int · returned tuple · level recorded, date not recorded
parse_model in 6 papers main_mnist_cifar.py ran; the contract check could not run (DEP_MISSING) · metamorphic tier: deterministic no licence file found · pointer only · ec8a09099cf40ac2 · report fixture: signature args:str/0/str, dataset:NoneType/0/? · returned Linear · level recorded, date not recorded
repackage_hidden in 31 papers
census: 5 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
main_lstm.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ec9329606c156d1d · report fixture: signature h:Tensor/2/float · returned Tensor · level recorded, date not recorded
sum_of_square_grad algorithm.py ran · honoured contract no licence file found · pointer only · 64af453cacc5f615 · report fixture: signature grads:list/1/Tensor · returned Tensor · level recorded 2026-09-22
update_momentum algorithm.py ran · our draft was wrong no licence file found · pointer only · 3d552685e82f026d · report fixture: signature grad:Tensor/2/float, state:dict/0/?, momentum:float/0/float · returned Tensor · level recorded 2026-09-22
AlgorithmBase algorithm.py unverified no licence file found · pointer only · 9ab5f783e4f918a3 · report
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
main_imagenet.py unverified no licence file found · pointer only · 9b8289076669fe4f · report
validate in 313 papers main_imagenet.py unverified no licence file found · pointer only · 5118f5ac5157ed29 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for general framework to study the clipping algorithms (graph method: general framework to study the clipping algorithms), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.

label matches by construction: the code was generated for this method (not judged by a model)

  1. clipping_framework_update entry · level 3 · ran · violated contract · 32268f09350d54a66c29975feab45f90bbc0956ab72c7b71c1915610a3e2af4a

harvested Assembly for general framework to study the clipping algorithms (graph method: general framework to study the clipping algorithms). 4 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. SGDClip entry · level 1 · ran · 2f2b5b01c14d1c34
  2. AlgorithmBase helper · level 0 · unverified · 9ab5f783e4f918a3
  3. sum_of_square_grad helper · level 1 · ran · honoured contract · 64af453cacc5f615
  4. update_momentum update_rule · level 1 · ran · our draft was wrong · 3d552685e82f026d

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="2010.02519") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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