SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.07547 · ICLR · 2025

Instance-dependent Early Stopping

Lei Feng, Bo Han, Tongliang Liu, Runqi Lin, Suqin Yuan

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 1 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/2502.07547.json · badge: /api/ran/2502.07547.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
tmllab/2025_iclr_ies canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
tmllab/2025_ICLR_IES marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
correct_moving_average_new_new Ran
ran; our contract draft was wrong, not the code
tmllab/2025_ICLR_IES/cifar_main.py
pointer only (licence: NONE) · get_code("f5b3070a95cfbfea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2025_ICLR_IES 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_cifar10_dataset Ran
ran; our contract draft was wrong, not the code
tmllab/2025_iclr_ies/cifar_main.py
pointer only (licence: NONE) · get_code("c8fbf107d9014e50")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2025_iclr_ies 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.

unpickle Ran
ran; our contract draft was wrong, not the code
tmllab/2025_iclr_ies/cifar_main.py
pointer only (licence: NONE) · get_code("10b1d9fe0289ed97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2025_iclr_ies 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_cifar100_dataset Not yet run
unverified (harvested, no recorded run)
tmllab/2025_iclr_ies/cifar_main.py
pointer only (licence: NONE) · get_code("84b9b4ea0c4d35bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2025_iclr_ies 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

In machine learning practice, early stopping has been widely used to regularize models and can save computational costs by halting the training process when the model's performance on a validation set stops improving. However, conventional early stopping applies the same stopping criterion to all instances without considering their individual learning statuses, which leads to redundant computations on instances that are already well-learned. To further improve the efficiency, we propose an Instance-dependent Early Stopping (IES) method that adapts the early stopping mechanism from the entire training set to the instance level, based on the core principle that once the model has mastered an instance, the training on it should stop. IES considers an instance as mastered if the second-order differences of its loss value remain within a small range around zero. This offers a more consistent measure of an instance's learning status compared with directly using the loss value, and thus allows for a unified threshold to determine when an instance can be excluded from further backpropagation. We show that excluding mastered instances from backpropagation can increase the gradient norms, thereby accelerating the decrease of the training loss and speeding up the training process. Extensive experiments on benchmarks demonstrate that IES method can reduce backpropagation instances by 10%-50% while maintaining or even slightly improving the test accuracy and transfer learning performance of a model. Our implementation can be found at https://github.com/tmllab/2025_ICLR_IES.

For agents

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

get_harvested_code_for_paper("2502.07547")
get_code_for_paper("2502.07547")
have("2502.07547")

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

curl https://syntology.ai/api/ran/2502.07547.json

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

[![Syntology run record](https://syntology.ai/api/ran/2502.07547.svg)](https://syntology.ai/paper/2502.07547)

Connect an agent — have() is free.