Papers › "Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent...

"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach

1 Mar 2024arXiv:2403.00258archive 2025-07-28

Lingyu Gu, Yongqi Du, Yuan Zhang, Di Xie, ShiLiang Pu, Robert C. Qiu, Zhenyu Liao

Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and inference more computationally challenging. In an attempt to address this key limitation, efforts have been devoted to the compression (e.g., sparsification and/or quantization) of these large-scale machine learning models, so that they can be deployed on low-power IoT devices. In this paper, building upon recent advances in neural tangent kernel (NTK) and random matrix theory (RMT), we provide a novel compression approach to wide and fully-connected deep neural nets. Specifically, we demonstrate that in the high-dimensional regime where the number of data points n and their dimension p are both large, and under a Gaussian mixture model for the data, there exists asymptotic spectral equivalence between the NTK matrices for a large family of DNN models. This theoretical result enables "lossless" compression of a given DNN to be performed, in the sense that the compressed network yields asymptotically the same NTK as the original (dense and unquantized) network, with its weights and activations taking values only in { 0, ±1 } up to a scaling. Experiments on both synthetic and real-world data are conducted to support the advantages of the proposed compression scheme, with code available at https://github.com/Model-Compression/Lossless_Compression.

PaperPDFCodeCode 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 8 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 7 ran (6 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.

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

model-compression/lossless_compression officialmentioned in paperpytorchSyntology: 8 samples, 7 ran (1 instrument-failed) · 1 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

8 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; 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
6ran
1unverified

Licence: 0 of the 8 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 model-compression/lossless_compression. “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.

model-compression/lossless_compression official repository 8 samples, 7 ran (1 instrument-failed) · 1 unverified
act0 code/compression/new_MNIST/model.py ran Apache-2.0 (permissive) · 35677cba1e295c94 · report fixture: signature x:float/0/float, s1:float/0/float, s2:float/0/float, a:float/0/float · returned int · level recorded 2026-09-24
act1 code/compression/new_MNIST/model.py ran Apache-2.0 (permissive) · 8c221678ed830a4e · report fixture: signature x:float/0/float, r1:float/0/float, r2:float/0/float, r3:float/0/float, r4:float/0/float, b1:float/0/float, b2:float/0/float · returned int · level recorded 2026-09-24
gen_stat code/compression/new_MNIST/GMM_data.py ran Apache-2.0 (permissive) · ec59522d270a6220 · report fixture: signature testcase:str/0/str, selected_target:list/1/int, T:int/0/int, p:int/0/int, cs:list/1/float, means:NoneType/0/?, covs:NoneType/0/? · returned tuple · level recorded 2026-09-24
get_act0 code/compression/new_MNIST/matching.py ran · our draft was wrong Apache-2.0 (permissive) · 70063516694a789d · report fixture: signature tao_last:float/0/float · returned tuple · level recorded 2026-09-24
get_act1 code/compression/new_MNIST/matching.py ran Apache-2.0 (permissive) · b711b34c83ced175 · report fixture: signature b1:float/0/float, b2:float/0/float, tao_last:float/0/float · returned tuple · level recorded 2026-09-24
get_or_param code/compression/new_MNIST/matching.py ran Apache-2.0 (permissive) · 4433b4ebece14dd3 · report fixture: signature L:int/0/int, act:str/0/str, tau_0:float/0/float · returned tuple · level recorded 2026-09-24
ternary_weights code/compression/new_MNIST/model.py ran Apache-2.0 (permissive) · 5e72c2565206e3f7 · report fixture: signature initialization_way:str/0/str, kesi:float/0/float, W:Tensor/2/float · returned Tensor · level recorded 2026-09-24
gen_data in 14 papers code/compression/new_MNIST/GMM_data.py unverified Apache-2.0 (permissive) · 03518593ba2ab3b7 · report

Tasks

Model CompressionQuantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

NTK

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