Papers › Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach

Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach

16 Apr 2018ICLR 2019 5arXiv:1804.05862archive 2025-07-28

Wenda Zhou, Victor Veitch, Morgane Austern, Ryan P. Adams, Peter Orbanz

Modern neural networks are highly overparameterized, with capacity to substantially overfit to training data. Nevertheless, these networks often generalize well in practice. It has also been observed that trained networks can often be "compressed" to much smaller representations. The purpose of this paper is to connect these two empirical observations. Our main technical result is a generalization bound for compressed networks based on the compressed size. Combined with off-the-shelf compression algorithms, the bound leads to state of the art generalization guarantees; in particular, we provide the first non-vacuous generalization guarantees for realistic architectures applied to the ImageNet classification problem. As additional evidence connecting compression and generalization, we show that compressibility of models that tend to overfit is limited: We establish an absolute limit on expected compressibility as a function of expected generalization error, where the expectations are over the random choice of training examples. The bounds are complemented by empirical results that show an increase in overfitting implies an increase in the number of bits required to describe a trained network.

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 15 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 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) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 15 samples from 1 repository, 2 ran (2 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 on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

wendazhou/nnet-compression-generalization officialmentioned in papermentioned on GitHubtfMITSyntology: 15 samples, 2 ran (0 instrument-failed) · 13 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

15 samples harvested: 2 ran (of which 0 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) · 13 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.

2ran
13unverified

Licence: 0 of the 15 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 wendazhou/nnet-compression-generalization. “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.

wendazhou/nnet-compression-generalization official repository 15 samples, 2 ran (0 instrument-failed) · 13 unverified
get_variable_summary nnet/compression/_utils.py ran MIT (permissive) · ded4b33f66d4a362 · report fixture: signature ckpt:MockCheckpoint/0/?, variable_names:list/1/str · returned DataFrame · level recorded 2026-09-25
normal_mixture_log_density nnet/compression/bounds.py ran fingerprinted MIT (permissive) · 3aa9e30dabef31ec · report fixture: signature x:ndarray/1/float, mu:ndarray/1/float, sigma:ndarray/1/float, weights:ndarray/1/float · returned ndarray · level recorded 2026-09-25
apply_noise in 5 papers nnet/compression/weights_noise.py unverified MIT (permissive) · b381672c9093d9a2 · report
compress_variable nnet/compression/coding.py unverified MIT (permissive) · 2101478dbafc6d87 · report
conv2d in 119 papers nnet/models/layers.py unverified MIT (permissive) · 541c4775c6d38c8d · report
dense in 22 papers nnet/models/layers.py unverified MIT (permissive) · d3ddbb49f3799d81 · report
depthwise_conv2d nnet/models/layers.py unverified MIT (permissive) · 805d0df53909c45b · report
divergence_gains nnet/compression/bounds.py unverified MIT (permissive) · 0762cbd6c131efd2 · report
get_bits_for_index nnet/compression/coding.py unverified MIT (permissive) · fb7158160fe2bc4c · report
get_index_list nnet/compression/coding.py unverified MIT (permissive) · 6dd0b27e22163eeb · report
get_variable_compression_summary nnet/compression/_utils.py unverified MIT (permissive) · 1e6a6fc9f23a0b38 · report
get_variable_compression_summary nnet/compression/mnist.py unverified MIT (permissive) · 6bd8759ef432fe94 · report
get_variable_summary nnet/compression/mnist.py unverified MIT (permissive) · 53ff94be1d2c857d · report
noisy_variable_getter nnet/compression/weights_noise.py unverified MIT (permissive) · 3095b0b49905d9e6 · report
normal_kl_divergence nnet/compression/bounds.py unverified MIT (permissive) · c3ed202dd1ee6bb9 · report

Tasks

Generalization Bounds

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