SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1802.10399 · 2018

Compressing Neural Networks using the Variational Information Bottleneck

arXiv · PDF · Open in the Atlas

Code that ran

1 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 1 has no contract verdict; 0 failures of our instrument; 2 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/1802.10399.json · badge: /api/ran/1802.10399.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
zhuchen03/VIBNet community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
FunctionStatusWhere it lives
reparameterize Ran
ran on a synthesized input
zhuchen03/VIBNet/ib_layers.py
code served (permissive licence) · get_code("a744358ed458a3a2")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
from torch.autograd import Variable

torch.manual_seed(0)

# Analyze the function:
# - mu: tensor, used with .view(1, -1), needs to be 1D or compatible
# - logvar: tensor, used with .mul(0.5).exp_() and .view(1, -1)
# - batch_size: int, used to create FloatTensor(batch_size, std.size(0))
# - cuda: bool, default False
# - sampling: bool, default True

# Create small tensors with distinct dimensions
# mu and logvar should be 1D tensors representing latent dimension
latent_dim = 4
mu = torch.randn(latent_dim)
logvar = torch.randn(latent_dim)
batch_size = 2
cuda = False
sampling = True

ARGS = {
    "mu": mu,
    "logvar": logvar,
    "batch_size": batch_size,
    "cuda": cuda,
    "sampling": sampling
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
accuracy Not yet run
unverified (harvested, no recorded run)
zhuchen03/VIBNet/ib_vgg_train.py
code served (permissive licence) · get_code("f0c9a29156911331")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
zhuchen03/VIBNet/ib_vgg_train.py
code served (permissive licence) · get_code("56d9dbf9f393fbeb")
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 (1 with at least one paper dated earlier, 1 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
accuracy 71 other papers
2 dated earlier, 1 the same month, 68 later · 2 only as an assembly brick
1505.05424 (2015-05)
Weight Uncertainty in Neural Networks
1705.07204 (2017-05)
Ensemble Adversarial Training: Attacks and Defenses
1802.10419 (2018-02)
Convolutional Neural Networks with Alternately Updated Clique
and 68 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

Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture. In this paper we focus on pruning individual neurons, which can simultaneously trim model size, FLOPs, and run-time memory. To improve upon the performance of existing compression algorithms we utilize the information bottleneck principle instantiated via a tractable variational bound. Minimization of this information theoretic bound reduces the redundancy between adjacent layers by aggregating useful information into a subset of neurons that can be preserved. In contrast, the activations of disposable neurons are shut off via an attractive form of sparse regularization that emerges naturally from this framework, providing tangible advantages over traditional sparsity penalties without contributing additional tuning parameters to the energy landscape. We demonstrate state-of-the-art compression rates across an array of datasets and network architectures.

For agents

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

get_harvested_code_for_paper("1802.10399")
get_code_for_paper("1802.10399")
have("1802.10399")

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

curl https://syntology.ai/api/ran/1802.10399.json

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

[![Syntology run record](https://syntology.ai/api/ran/1802.10399.svg)](https://syntology.ai/paper/1802.10399)

Connect an agent — have() is free.