SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1803.09820 · 2018

A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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, 1 violated it and 1 has no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-22; 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/1803.09820.json · badge: /api/ran/1803.09820.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
GilesStrong/Smith_HyperParams1_Demo reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
AlexMGitHub/Checkers-MCTS community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
csvance/onecycle-cosine extension (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
ifrit98/lr_range_test reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
AMS Ran
ran, honoured the contract we drafted
GilesStrong/Smith_HyperParams1_Demo/Modules/AMS.py
code served (permissive licence) · get_code("3dbd243a8c21052a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import math

# The function AMS takes two numeric parameters: s (signal) and b (background)
# Both should be positive numbers for the calculation to make sense
# Let's use simple float values

s = 50.0
b = 100.0

ARGS = {
    's': s,
    'b': b
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
amsScanQuick Ran
ran; our contract draft was wrong, not the code
GilesStrong/Smith_HyperParams1_Demo/Modules/AMS.py
code served (permissive licence) · get_code("a5ca0276a41b2558")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pandas as pd
import numpy as np

# Create a small DataFrame that mimics the structure expected by amsScanQuick
# The function expects:
# - 'gen_target' column (0 or 1)
# - 'gen_weight' column (numeric weights)
# - 'pred_class' column (predicted class probabilities/scores)

np.random.seed(0)

n_samples = 10

inData = pd.DataFrame({
    'gen_target': np.random.randint(0, 2, size=n_samples),
    'gen_weight': np.random.uniform(0.5, 2.0, size=n_samples),
    'pred_class': np.random.uniform(0, 1, size=n_samples)
})

wFactor = 250000.0 / 50000.0

ARGS = {
    'inData': inData,
    'wFactor': wFactor
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
annealing_cos Ran
ran, violated the contract we drafted
csvance/onecycle-cosine/onecyclec.py
pointer only (licence: NONE) · get_code("c12d423641e370fe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, csvance/onecycle-cosine 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.

save_nn_to_disk Ran
ran on a synthesized input
AlexMGitHub/Checkers-MCTS/training_pipeline.py
code served (permissive licence) · get_code("ef6d4cd8f9f23f77")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from datetime import datetime

# Create a minimal neural network with a save method
class MinimalNeuralNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)
    
    def save(self, filename):
        # Mock save method that does nothing (avoids actual file I/O)
        pass

torch.manual_seed(0)

# Create instances for the function arguments
neural_network = MinimalNeuralNetwork()
iteration = 42
timestamp = "2024_01_15_10_30_45"

ARGS = {
    "neural_network": neural_network,
    "iteration": iteration,
    "timestamp": timestamp
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
plot_history Not yet run
unverified (harvested, no recorded run)
AlexMGitHub/Checkers-MCTS/training_pipeline.py
code served (permissive licence) · get_code("ba3cf0e825859191")
How it ran

no invocation recorded.

ploty Not yet run
unverified (harvested, no recorded run)
ifrit98/lr_range_test/lr_range_test/plot.py
pointer only (licence: NONE) · get_code("01862d3a9e702e3b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ifrit98/lr_range_test 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.

states_to_piece_positions Not yet run
unverified (harvested, no recorded run)
AlexMGitHub/Checkers-MCTS/play_Checkers.py
code served (permissive licence) · get_code("13b8695d58380dd5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

Although deep learning has produced dazzling successes for applications of image, speech, and video processing in the past few years, most trainings are with suboptimal hyper-parameters, requiring unnecessarily long training times. Setting the hyper-parameters remains a black art that requires years of experience to acquire. This report proposes several efficient ways to set the hyper-parameters that significantly reduce training time and improves performance. Specifically, this report shows how to examine the training validation/test loss function for subtle clues of underfitting and overfitting and suggests guidelines for moving toward the optimal balance point. Then it discusses how to increase/decrease the learning rate/momentum to speed up training. Our experiments show that it is crucial to balance every manner of regularization for each dataset and architecture. Weight decay is used as a sample regularizer to show how its optimal value is tightly coupled with the learning rates and momentums. Files to help replicate the results reported here are available.

For agents

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

get_harvested_code_for_paper("1803.09820")
get_code_for_paper("1803.09820")
have("1803.09820")

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

curl https://syntology.ai/api/ran/1803.09820.json

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

[![Syntology run record](https://syntology.ai/api/ran/1803.09820.svg)](https://syntology.ai/paper/1803.09820)

Connect an agent — have() is free.