SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.01345 · NeurIPS · 2024

BMRS: Bayesian Model Reduction for Structured Pruning

Raghavendra Selvan, Christian Igel, Dustin Wright

arXiv · PDF · Open in the Atlas

Code that ran

11 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 9 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 0 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/2406.01345.json · badge: /api/ran/2406.01345.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
saintslab/bmrs-structured-pruning canonical (classifier label)
classifier basis: classifier_2025
11 ran · 0 no recorded run
FunctionStatusWhere it lives
Etheta Ran
ran, honoured the contract we drafted
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("b4fac9801138a0cd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

LogUniformApproximateDiracBMRPruningLayer Ran
ran on a synthesized input · constructed an object; no result was computed
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("6acafad15c4789d3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

Phi Ran
ran, honoured the contract we drafted
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("4b2929f719750d8a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

Phi_inv Ran
ran, honoured the contract we drafted
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("1578c441ee66a2c3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

calculate_model_kl Ran
ran, honoured the contract we drafted
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("07d6377d231bd408")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

erfcx Ran
ran, honoured the contract we drafted
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("e4ccef0f9ddf163c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

gather_pruning_layers Ran
ran, honoured the contract we drafted
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("6478df241893f8ce")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

get_weight_l2 Ran
ran, honoured the contract we drafted
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("a62d90c72e6633f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

kldiv Ran
ran, honoured the contract we drafted
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("fbe81395901bb87a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

phi Ran
ran, honoured the contract we drafted
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("3f5012a9ea5a467a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

reparameterize Ran
ran; our contract draft was wrong, not the code
saintslab/bmrs-structured-pruning/modules/layers.py
pointer only (licence: NONE) · get_code("d71a61ef4305cdc5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saintslab/bmrs-structured-pruning 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.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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

Modern neural networks are often massively overparameterized leading to high compute costs during training and at inference. One effective method to improve both the compute and energy efficiency of neural networks while maintaining good performance is structured pruning, where full network structures (e.g. neurons or convolutional filters) that have limited impact on the model output are removed. In this work, we propose Bayesian Model Reduction for Structured pruning (BMRS), a fully end-to-end Bayesian method of structured pruning. BMRS is based on two recent methods: Bayesian structured pruning with multiplicative noise, and Bayesian model reduction (BMR), a method which allows efficient comparison of Bayesian models under a change in prior. We present two realizations of BMRS derived from different priors which yield different structured pruning characteristics: 1) BMRS N with the truncated log-normal prior, which offers reliable compression rates and accuracy without the need for tuning any thresholds and 2) BMRS U with the truncated log-uniform prior that can achieve more aggressive compression based on the boundaries of truncation. Overall, we find that BMRS offers a theoretically grounded approach to structured pruning of neural networks yielding both high compression rates and accuracy. Experiments on multiple datasets and neural networks of varying complexity showed that the two BMRS methods offer a competitive performance-efficiency trade-off compared to other pruning methods. 1

For agents

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

get_harvested_code_for_paper("2406.01345")
get_code_for_paper("2406.01345")
have("2406.01345")

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

curl https://syntology.ai/api/ran/2406.01345.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.01345.svg)](https://syntology.ai/paper/2406.01345)

Connect an agent — have() is free.