SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.08709 · ICML · 2020

Do We Need Zero Training Loss After Achieving Zero Training Error?

Masashi Sugiyama, Gang Niu, Takashi Ishida, Ikko Yamane, Tomoya Sakai

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2002.08709.json · badge: /api/ran/2002.08709.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
takashiishida/flooding canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
acc_check Ran
ran, honoured the contract we drafted
takashiishida/flooding/utils/utils_algo.py
pointer only (licence: GPL-3.0) · get_code("eb5562f1be997c5e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, takashiishida/flooding, is not in the permissive set Syntology serves inline. 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.

epoch_time Ran
ran, honoured the contract we drafted
takashiishida/flooding/utils/utils_algo.py
pointer only (licence: GPL-3.0) · get_code("3e21e6589663b136")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, takashiishida/flooding, is not in the permissive set Syntology serves inline. 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_grads Ran
ran; our contract draft was wrong, not the code
takashiishida/flooding/utils/utils_algo.py
pointer only (licence: GPL-3.0) · get_code("d251cab596a514b3")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, takashiishida/flooding, is not in the permissive set Syntology serves inline. 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.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
epoch_time 10 other papers
2 dated earlier, 8 later
1608.07017 (2016-08)
Ambient Sound Provides Supervision for Visual Learning
1911.05343 (2019-11)
A Stable Variational Autoencoder for Text Modelling
2010.12229 (2020-10)
Throughput-Optimal Topology Design for Cross-Silo Federated Learning
and 7 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 2026-11-21.

Repositories linked to this paper

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

Abstract

Overparameterized deep networks have the capacity to memorize training data with zero training error. Even after memorization, the training loss continues to approach zero, making the model overconfident and the test performance degraded. Since existing regularizers do not directly aim to avoid zero training loss, it is hard to tune their hyperparameters in order to maintain a fixed/preset level of training loss. We propose a direct solution called flooding that intentionally prevents further reduction of the training loss when it reaches a reasonably small value, which we call the flood level. Our approach makes the loss float around the flood level by doing mini-batched gradient descent as usual but gradient ascent if the training loss is below the flood level. This can be implemented with one line of code and is compatible with any stochastic optimizer and other regularizers. With flooding, the model will continue to "random walk" with the same non-zero training loss, and we expect it to drift into an area with a flat loss landscape that leads to better generalization. We experimentally show that flooding improves performance and, as a byproduct, induces a double descent curve of the test loss.

For agents

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

get_harvested_code_for_paper("2002.08709")
get_code_for_paper("2002.08709")
have("2002.08709")

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

curl https://syntology.ai/api/ran/2002.08709.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.08709.svg)](https://syntology.ai/paper/2002.08709)

Connect an agent — have() is free.