Papers › Pruning neural networks without any data by iteratively conserving synaptic flow

Pruning neural networks without any data by iteratively conserving synaptic flow

9 Jun 2020NeurIPS 2020 12arXiv:2006.05467archive 2025-07-28

Hidenori Tanaka, Daniel Kunin, Daniel L. K. Yamins, Surya Ganguli

Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy both during training and at test time. Recent works have identified, through an expensive sequence of training and pruning cycles, the existence of winning lottery tickets or sparse trainable subnetworks at initialization. This raises a foundational question: can we identify highly sparse trainable subnetworks at initialization, without ever training, or indeed without ever looking at the data? We provide an affirmative answer to this question through theory driven algorithm design. We first mathematically formulate and experimentally verify a conservation law that explains why existing gradient-based pruning algorithms at initialization suffer from layer-collapse, the premature pruning of an entire layer rendering a network untrainable. This theory also elucidates how layer-collapse can be entirely avoided, motivating a novel pruning algorithm Iterative Synaptic Flow Pruning (SynFlow). This algorithm can be interpreted as preserving the total flow of synaptic strengths through the network at initialization subject to a sparsity constraint. Notably, this algorithm makes no reference to the training data and consistently competes with or outperforms existing state-of-the-art pruning algorithms at initialization over a range of models (VGG and ResNet), datasets (CIFAR-10/100 and Tiny ImageNet), and sparsity constraints (up to 99.99 percent). Thus our data-agnostic pruning algorithm challenges the existing paradigm that, at initialization, data must be used to quantify which synapses are important.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (ganguli-lab/Synaptic-Flow) is linked to this paper; the 17 samples below come from 5 community repositories. Syntology harvested code from ganguli-lab/Synaptic-Flow for 2 other papers.

ganguli-lab/Synaptic-Flow: Syntology's graph links these samples to SNIP: Single-shot Network Pruning based on Connection Sensitivity (arXiv:1810.02340; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified) and Zeroth-Order Topological Insights into Iterative Magnitude Pruning (arXiv:2206.06563; that paper's own run record: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method.

Syntology 17 code samples harvested from 5 repositories linked to this paper: 12 ran (of which 5 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 17 samples from 5 repositories, 12 ran (11 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ganguli-lab/Synaptic-Flow officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SNIP: Single-shot Network Pruning based on Connection Sensitivity (arXiv:1810.02340; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified) and Zeroth-Order Topological Insights into Iterative Magnitude Pruning (arXiv:2206.06563; that paper's own run record: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
Hoonyyhoon/Comparison-of-Synflow_SNIP_GraSP mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
apd10/synaptic-flow mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
iurada/px-ntk-pruning mentioned on GitHubpytorchSyntology: 11 samples, 7 ran (1 instrument-failed) · 4 unverified report
pvh1602/npb mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
yitewang/ntk-sap mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

17 samples harvested: 12 ran (of which 5 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
11ran
5unverified

Licence: 16 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Hoonyyhoon/Comparison-of-Synflow_SNIP_GraSP community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
Synflow pruning_method/Synflow.py ran no licence file found · pointer only · 772bf8519445187f · report fixture: returned Synflow · level recorded 2026-09-22
Pruner in 8 papers pruning_method/Synflow.py unverified no licence file found · pointer only · 80f512af69686019 · report
apd10/synaptic-flow community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SynFlow Pruners/pruners.py ran no licence file found · pointer only · e7ca315e78c80c60 · report fixture: returned SynFlow · level recorded 2026-09-22
iurada/px-ntk-pruning community (archive-listed) 11 samples, 7 ran (1 instrument-failed) · 4 unverified
BatchNorm1d lib/pruners.py ran · metamorphic tier: invariant no licence file found · pointer only · 7935d0e889ff9eee · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22
BatchNorm2d in 9 papers lib/pruners.py ran no licence file found · pointer only · bd2e9ef9ef047b34 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
lib/pruners.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · d526bce01cf543a6 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Identity1d lib/pruners.py ran · metamorphic tier: invariant no licence file found · pointer only · c09e99a71aca360c · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Identity2d lib/pruners.py ran · metamorphic tier: invariant no licence file found · pointer only · f3d19807c24c2f63 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Linear in 127 papers lib/pruners.py ran · metamorphic tier: invariant no licence file found · pointer only · dc24efa85753be6b · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22
masks lib/pruners.py ran · our draft was wrong no licence file found · pointer only · b4642e3b07dce20e · report fixture: signature module:callable/0/? · returned generator · level recorded 2026-09-22
Pruner in 8 papers lib/pruners.py unverified no licence file found · pointer only · 895223082b0c7453 · report
SynFlow lib/pruners.py unverified no licence file found · pointer only · 60c6b324705c2d2b · report
masked_parameters lib/pruners.py unverified no licence file found · pointer only · 3df869cac18fe082 · report
prunable lib/pruners.py unverified no licence file found · pointer only · 3127d6e8725313f3 · report
pvh1602/npb community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Pruner in 8 papers Pruners/pruners.py ran no licence file found · pointer only · e28e1790d31fe600 · report fixture: returned Pruner · level recorded 2026-09-22
SynFlow Pruners/pruners.py ran no licence file found · pointer only · 80271ea817e0be5e · report fixture: returned SynFlow · level recorded 2026-09-22
yitewang/ntk-sap community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SynFlow Pruners/pruners.py ran MIT (permissive) · 97a5db95987dac5b · report fixture: returned SynFlow · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

5 assemblies on this paper: 5 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

5 sibling assemblies for Iterative Synaptic Flow Pruning (SynFlow) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Iterative Synaptic Flow Pruning (SynFlow) (graph method: Iterative Synaptic Flow Pruning (SynFlow)). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. SynFlow entry · level 1 · ran · 80271ea817e0be5e
  2. Pruner helper · level 1 · ran · e28e1790d31fe600

harvested Assembly for Iterative Synaptic Flow Pruning (SynFlow) (graph method: Iterative Synaptic Flow Pruning (SynFlow)). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. SynFlow entry · level 1 · ran · e7ca315e78c80c60
  2. Pruner helper · level 1 · ran · 25100e43d36881c9

harvested Assembly for Iterative Synaptic Flow Pruning (SynFlow) (graph method: Iterative Synaptic Flow Pruning (SynFlow)). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. SynFlow entry · level 1 · ran · 97a5db95987dac5b
  2. Pruner helper · level 1 · ran · 25100e43d36881c9

harvested Assembly for Iterative Synaptic Flow Pruning (SynFlow) (graph method: Iterative Synaptic Flow Pruning (SynFlow)). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. Synflow entry · level 1 · ran · 772bf8519445187f
  2. Pruner helper · level 0 · unverified · 80f512af69686019

harvested Assembly for Iterative Synaptic Flow Pruning (SynFlow) (graph method: Iterative Synaptic Flow Pruning (SynFlow)). 12 bricks; individually on a fixture: 8 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. SynFlow entry · level 0 · unverified · 60c6b324705c2d2b
  2. Pruner helper · level 0 · unverified · 895223082b0c7453
  3. masked_parameters helper · level 0 · unverified · 3df869cac18fe082
  4. masks helper · level 1 · ran · our draft was wrong · b4642e3b07dce20e
  5. prunable helper · level 0 · unverified · 3127d6e8725313f3
  6. BatchNorm1d helper · level 1 · ran · 7935d0e889ff9eee
  7. BatchNorm2d helper · level 1 · ran · bd2e9ef9ef047b34
  8. Conv2d helper · level 1 · ran · d526bce01cf543a6
  9. Identity1d helper · level 1 · ran · c09e99a71aca360c
  10. Identity2d helper · level 1 · ran · f3d19807c24c2f63
  11. Linear helper · level 1 · ran · dc24efa85753be6b
  12. dotdict helper · level 1 · ran · 11384de9305bcd32

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2006.05467") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Pruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections