SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.07804 · NeurIPS · 2021

Scaling Up Exact Neural Network Compression by ReLU Stability

Xin Yu, Thiago Serra, Abhinav Kumar, Srikumar Ramalingam

arXiv · PDF · Open in the Atlas

Code that ran

3 of 8 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, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 5 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/2102.07804.json · badge: /api/ran/2102.07804.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
yuxwind/exactcompression canonical (classifier label)
classifier basis: classifier_2025
3 ran · 5 no recorded run
FunctionStatusWhere it lives
find_independ_rows Ran
ran, honoured the contract we drafted
yuxwind/exactcompression/prune_network.py
pointer only (licence: NONE) · get_code("78fd65e96ec8ebff")
How it ran

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

parse_line Ran
ran; our contract draft was wrong, not the code
yuxwind/exactcompression/get_activation_patterns.py
pointer only (licence: NONE) · get_code("f745cdc193c5f937")
How it ran

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

prune_inactive_per_layer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yuxwind/exactcompression/prune_network.py
pointer only (licence: NONE) · get_code("d2734b8d652d3d28")
How it ran

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

accuracy Not yet run
unverified (harvested, no recorded run)
yuxwind/exactcompression/train_fcnn.py
pointer only (licence: NONE) · get_code("469bf48752905889")
How it ran

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

get_features Not yet run
unverified (harvested, no recorded run)
yuxwind/exactcompression/train_fcnn.py
pointer only (licence: NONE) · get_code("2893257a02af7980")
How it ran

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

parse_file Not yet run
unverified (harvested, no recorded run)
yuxwind/exactcompression/get_activation_patterns.py
pointer only (licence: NONE) · get_code("d04f5ead368dc743")
How it ran

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

prune_active_per_layer Not yet run
unverified (harvested, no recorded run)
yuxwind/exactcompression/prune_network.py
pointer only (licence: NONE) · get_code("b386ef159cae2024")
How it ran

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

validate Not yet run
unverified (harvested, no recorded run)
yuxwind/exactcompression/train_fcnn.py
pointer only (licence: NONE) · get_code("43483040e905c664")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuxwind/exactcompression 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 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.

FunctionAlso present inEarliest-datedOthers named
accuracy 71 other papers
43 dated earlier, 26 later, 2 same year, order not determinable · 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
1802.10399 (2018-02)
Compressing Neural Networks using the Variational Information Bottleneck
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

We can compress a rectifier network while exactly preserving its underlying functionality with respect to a given input domain if some of its neurons are stable. However, current approaches to determine the stability of neurons with Rectified Linear Unit (ReLU) activations require solving or finding a good approximation to multiple discrete optimization problems. In this work, we introduce an algorithm based on solving a single optimization problem to identify all stable neurons. Our approach is on median 183 times faster than the state-of-art method on CIFAR-10, which allows us to explore exact compression on deeper (5 × 100) and wider (2 × 800) networks within minutes. For classifiers trained under an amount of 1 regularization that does not worsen accuracy, we can remove up to 56% of the connections on the CIFAR-10 dataset. The code is available at the following link, https://github.com/yuxwind/ExactCompression.

For agents

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

get_harvested_code_for_paper("2102.07804")
get_code_for_paper("2102.07804")
have("2102.07804")

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

curl https://syntology.ai/api/ran/2102.07804.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.07804.svg)](https://syntology.ai/paper/2102.07804)

Connect an agent — have() is free.