Papers › Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition

Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition

23 Jul 2021NeurIPS 2021 12arXiv:2107.11442archive 2025-07-28

Lucas Liebenwein, Alaa Maalouf, Oren Gal, Dan Feldman, Daniela Rus

We present a novel global compression framework for deep neural networks that automatically analyzes each layer to identify the optimal per-layer compression ratio, while simultaneously achieving the desired overall compression. Our algorithm hinges on the idea of compressing each convolutional (or fully-connected) layer by slicing its channels into multiple groups and decomposing each group via low-rank decomposition. At the core of our algorithm is the derivation of layer-wise error bounds from the Eckart Young Mirsky theorem. We then leverage these bounds to frame the compression problem as an optimization problem where we wish to minimize the maximum compression error across layers and propose an efficient algorithm towards a solution. Our experiments indicate that our method outperforms existing low-rank compression approaches across a wide range of networks and data sets. We believe that our results open up new avenues for future research into the global performance-size trade-offs of modern neural networks. Our code is available at https://github.com/lucaslie/torchprune.

PaperPDFConference PDFCodeCode Syntology ran

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

Syntology 12 code samples harvested from 2 repositories linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 3 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 9 samples from 1 repository, 3 ran (3 with no instrument failure; 0 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.

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lucaslie/torchprune officialmentioned in papermentioned on GitHubpytorchMITSyntology: 3 samples, 0 ran · 3 unverified report
lucaslie/provable_pruning mentioned on GitHubpytorchMITSyntology: 9 samples, 3 ran (0 instrument-failed) · 6 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.

Code Syntology ran Syntology

12 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 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.

3ran
9unverified

Licence: 0 of the 12 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 2 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.

lucaslie/torchprune official repository 3 samples, 0 ran · 3 unverified
flatten_all_but_last src/torchprune/torchprune/util/tensor.py unverified MIT (permissive) · cd21fa496ee07f67 · report
get_slice src/torchprune/torchprune/util/tensor.py unverified MIT (permissive) · fec5d06c6e4059e2 · report
to in 15 papers src/torchprune/torchprune/util/tensor.py unverified MIT (permissive) · e32720b53dfa1acf · report
lucaslie/provable_pruning community (archive-listed) 9 samples, 3 ran (0 instrument-failed) · 6 unverified
get_fig_name paper/alds/script/retrain_sweep.py ran fingerprinted MIT (permissive) · e7aaec08393471a8 · report fixture: signature title:str/0/str, tag:str/0/str · returned str · level recorded 2026-09-25
key_files paper/alds/script/results_viewer.py ran fingerprinted MIT (permissive) · 4ba3c7ec40d48b25 · report fixture: signature item:str/0/str · returned int · level recorded 2026-09-26
key_files paper/alds/script/retrain_sweep.py ran fingerprinted MIT (permissive) · ef6a9bde1b92ea8d · report fixture: signature item:str/0/str · returned int · level recorded 2026-09-26
gather_images paper/lost/script/eps_ball.py unverified MIT (permissive) · ef4646720ee554c1 · report
generate_noisy_images paper/lost/script/eps_ball.py unverified MIT (permissive) · 5aa7e295104184ca · report
get_fig_name paper/lost/script/generalization.py unverified MIT (permissive) · 32d86e992080431c · report
get_mesh in 5 papers paper/node/script/plots2d.py unverified MIT (permissive) · 8c4b0db81d1e76cd · report
make_f_hat paper/lost/script/eps_ball.py unverified MIT (permissive) · 8eec11df7c455a60 · report
prepare_data in 87 papers paper/node/script/plots2d.py unverified MIT (permissive) · 7257316eff0efa77 · report

Tasks

Low-rank compression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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