SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.04892 · 2019

Regularizing Neural Networks via Minimizing Hyperspherical Energy

arXiv · PDF · Open in the Atlas

Code that ran

2 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 1 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/1906.04892.json · badge: /api/ran/1906.04892.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
rmlin/CoMHE community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
load_test Ran
ran on a synthesized input
rmlin/CoMHE/adversarial_projection/cifar100_input_python.py
code served (permissive licence) · get_code("e2a9aaf74ba34fcd")
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 tuple. 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 numpy as np

# Construct a test dictionary that mimics the CIFAR-10 structure
# The function expects 'data' and 'fine_labels' keys
test = {
    'data': np.random.randint(0, 256, size=(8, 3072), dtype=np.uint8),  # 8 samples, 3*32*32 = 3072 features
    'fine_labels': np.array([0, 1, 2, 3, 4, 5, 6, 7], dtype=np.int64)  # 8 labels
}

batch_size = 2
i = 0

ARGS = {
    'test': test,
    'batch_size': batch_size,
    'i': i
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
load_train Ran
ran on a synthesized input
rmlin/CoMHE/adversarial_projection/cifar100_input_python.py
code served (permissive licence) · get_code("01a663a780ec75bf")
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 tuple. 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 numpy as np

# Create a small training dataset dictionary
# The function expects 'data' and 'fine_labels' keys
batch_size = 2
num_samples = 10

# Create synthetic image data: 10 samples of 3x32x32 images (flattened)
# Each image has 3 * 32 * 32 = 3072 values
image_data = np.random.randint(0, 256, size=(num_samples, 3 * 32 * 32), dtype=np.uint8)

# Create synthetic labels: 10 samples with class indices
labels = np.random.randint(0, 10, size=(num_samples,), dtype=np.int64)

train = {
    'data': image_data,
    'fine_labels': labels
}

i = 0

ARGS = {
    'train': train,
    'batch_size': batch_size,
    'i': i
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
loss2 Not yet run
unverified (harvested, no recorded run)
rmlin/CoMHE/adversarial_projection/loss.py
code served (permissive licence) · get_code("7bb2163a72b8b7cc")
How it ran

no invocation 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 (0 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
loss2 1 other paper
1 later
1910.13003 (2019-10)
Neural Similarity Learning

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

Inspired by the Thomson problem in physics where the distribution of multiple propelling electrons on a unit sphere can be modeled via minimizing some potential energy, hyperspherical energy minimization has demonstrated its potential in regularizing neural networks and improving their generalization power. In this paper, we first study the important role that hyperspherical energy plays in neural network training by analyzing its training dynamics. Then we show that naively minimizing hyperspherical energy suffers from some difficulties due to highly non-linear and non-convex optimization as the space dimensionality becomes higher, therefore limiting the potential to further improve the generalization. To address these problems, we propose the compressive minimum hyperspherical energy (CoMHE) as a more effective regularization for neural networks. Specifically, CoMHE utilizes projection mappings to reduce the dimensionality of neurons and minimizes their hyperspherical energy. According to different designs for the projection mapping, we propose several distinct yet well-performing variants and provide some theoretical guarantees to justify their effectiveness. Our experiments show that CoMHE consistently outperforms existing regularization methods, and can be easily applied to different neural networks.

For agents

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

get_harvested_code_for_paper("1906.04892")
get_code_for_paper("1906.04892")
have("1906.04892")

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

curl https://syntology.ai/api/ran/1906.04892.json

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

[![Syntology run record](https://syntology.ai/api/ran/1906.04892.svg)](https://syntology.ai/paper/1906.04892)

Connect an agent — have() is free.