SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.02519 · NeurIPS · 2020

Improved Analysis of Clipping Algorithms for Non-convex Optimization

Liwei Wang, Bohang Zhang, Jikai Jin, Cong Fang

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 7 failures of our instrument; 3 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2010.02519.json · badge: /api/ran/2010.02519.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
zbh2047/clipping-algorithms canonical (classifier label)
classifier basis: classifier_2025
9 ran · 3 no recorded run
FunctionStatusWhere it lives
SGDClip Ran
ran on a synthesized input
zbh2047/clipping-algorithms/algorithm.py
pointer only (licence: NONE) · get_code("2f2b5b01c14d1c34")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

batchify Ran
ran; our contract draft was wrong, not the code
zbh2047/clipping-algorithms/main_lstm.py
pointer only (licence: NONE) · get_code("96d4db57e5c2248f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_batch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zbh2047/clipping-algorithms/main_lstm.py
pointer only (licence: NONE) · get_code("f1095e1951238c8e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_algo Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zbh2047/clipping-algorithms/main_mnist_cifar.py
pointer only (licence: NONE) · get_code("8762f81d32460bc1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_dataset Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zbh2047/clipping-algorithms/main_mnist_cifar.py
pointer only (licence: NONE) · get_code("a01e88267842be7f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_model Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zbh2047/clipping-algorithms/main_mnist_cifar.py
pointer only (licence: NONE) · get_code("ec8a09099cf40ac2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

repackage_hidden Ran
ran; our contract draft was wrong, not the code
zbh2047/clipping-algorithms/main_lstm.py
pointer only (licence: NONE) · get_code("ec9329606c156d1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sum_of_square_grad Ran
ran, honoured the contract we drafted
zbh2047/clipping-algorithms/algorithm.py
pointer only (licence: NONE) · get_code("64af453cacc5f615")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

update_momentum Ran
ran; our contract draft was wrong, not the code
zbh2047/clipping-algorithms/algorithm.py
pointer only (licence: NONE) · get_code("3d552685e82f026d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

AlgorithmBase Not yet run
unverified (harvested, no recorded run)
zbh2047/clipping-algorithms/algorithm.py
pointer only (licence: NONE) · get_code("9ab5f783e4f918a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

accuracy Not yet run
unverified (harvested, no recorded run)
zbh2047/clipping-algorithms/main_imagenet.py
pointer only (licence: NONE) · get_code("9b8289076669fe4f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
zbh2047/clipping-algorithms/main_imagenet.py
pointer only (licence: NONE) · get_code("5118f5ac5157ed29")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zbh2047/clipping-algorithms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 4 the same month, 2 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
accuracy 80 other papers
46 dated earlier, 3 the same month, 31 later
1307.0414 (2013-07)
Challenges in Representation Learning: A report on three machine learning contests
1412.6553 (2014-12)
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
1503.02531 (2015-03)
Distilling the Knowledge in a Neural Network
and 77 more not named here
repackage_hidden 15 other papers
9 dated earlier, 2 the same month, 4 later
1609.04309 (2016-09)
Efficient softmax approximation for GPUs
1704.05119 (2017-04)
Exploring Sparsity in Recurrent Neural Networks
1803.08240 (2018-03)
An Analysis of Neural Language Modeling at Multiple Scales
and 12 more not named here
batchify 7 other papers
6 dated earlier, 1 the same month
1803.08240 (2018-03)
An Analysis of Neural Language Modeling at Multiple Scales
1805.04623 (2018-05)
Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context
1808.09029 (2018-08)
Pyramidal Recurrent Unit for Language Modeling
and 4 more not named here
get_batch 4 other papers
3 dated earlier, 1 the same month
1803.08240 (2018-03)
An Analysis of Neural Language Modeling at Multiple Scales
1810.09536 (2018-10)
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
1905.11881 (2019-05)
Why gradient clipping accelerates training: A theoretical justification for adaptivity
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, Zhang et al. [2020a] show that clipped (stochastic) Gradient Descent (GD) converges faster than vanilla GD/SGD via introducing a new assumption called (L 0 , L 1 )-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. * For clarity, we only present the dominating term (with respect to ε) here. * * For SGD, we further assume the gradient norm is upper bounded by M . * * * See section 3.3 for a detailed discussion of the lower bound.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2010.02519")
get_code_for_paper("2010.02519")
have("2010.02519")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2010.02519.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2010.02519.svg)](https://syntology.ai/paper/2010.02519)

Connect an agent — have() is free.