Papers › A path-norm toolkit for modern networks: consequences, promises and challenges

A path-norm toolkit for modern networks: consequences, promises and challenges

2 Oct 2023arXiv:2310.01225archive 2025-07-28

Antoine Gonon, Nicolas Brisebarre, Elisa Riccietti, Rémi Gribonval

This work introduces the first toolkit around path-norms that fully encompasses general DAG ReLU networks with biases, skip connections and any operation based on the extraction of order statistics: max pooling, GroupSort etc. This toolkit notably allows us to establish generalization bounds for modern neural networks that are not only the most widely applicable path-norm based ones, but also recover or beat the sharpest known bounds of this type. These extended path-norms further enjoy the usual benefits of path-norms: ease of computation, invariance under the symmetries of the network, and improved sharpness on layered fully-connected networks compared to the product of operator norms, another complexity measure most commonly used. The versatility of the toolkit and its ease of implementation allow us to challenge the concrete promises of path-norm-based generalization bounds, by numerically evaluating the sharpest known bounds for ResNets on ImageNet.

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 20 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 20 samples from 1 repository, 15 ran (15 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

agonon/pathnorm_toolkit officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: 20 samples, 15 ran (0 instrument-failed) · 5 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

20 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 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.

15ran
5unverified

Licence: 0 of the 20 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 agonon/pathnorm_toolkit. “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.

agonon/pathnorm_toolkit official repository 20 samples, 15 ran (0 instrument-failed) · 5 unverified
adaptive_pool_params repro/icml25/utils/pathnorm_transform.py ran fingerprinted BSD-3-Clause (permissive) · d504804f0f9ac808 · report fixture: signature in_size:int/0/int, out_size:int/0/int · returned tuple · level recorded 2026-09-24
check_imagenet_prepared repro/iclr24/utils/imagenet_data.py ran BSD-3-Clause (permissive) · 4af14115cc3aee7e · report fixture: signature root:str/0/str · returned ImageNetStatus · level recorded 2026-09-24
class_dir_name repro/iclr24/utils/download_imagenet_from_hf.py ran fingerprinted BSD-3-Clause (permissive) · 6e545c1bdc3f7cec · report fixture: signature label:int/0/int · returned str · level recorded 2026-09-24
count_files_recursive repro/iclr24/utils/imagenet_data.py ran BSD-3-Clause (permissive) · 6bbf2dc539716669 · report fixture: signature root:PosixPath/0/? · returned int · level recorded 2026-09-24
estimate_total_epoch_steps repro/iclr24/utils/train_imagenet.py ran BSD-3-Clause (permissive) · 3e27e0086ed49361 · report fixture: signature args:Args/0/? · returned int · level recorded 2026-09-24
format_duration in 11 papers repro/iclr24/utils/train_imagenet.py ran fingerprinted BSD-3-Clause (permissive) · 108ebe73d0b32ec2 · report fixture: signature seconds:float/0/float · returned str · level recorded 2026-09-24
get_imagenet_train_val_test repro/iclr24/utils/imagenet_dataset.py ran BSD-3-Clause (permissive) · cfe74f26307fd802 · report fixture: signature imagenet_data:str/0/str, blurred:bool/0/bool, randAugLevel:int/0/int · returned tuple · level recorded 2026-09-24
get_imagenet_transforms repro/iclr24/utils/imagenet_dataset.py ran fingerprinted BSD-3-Clause (permissive) · b417f83635432b4d · report fixture: signature randAugLevel:int/0/int · returned tuple · level recorded 2026-09-24
get_trainloader repro/iclr24/utils/pretrained_resnets.py ran BSD-3-Clause (permissive) · 15c4080169910373 · report fixture: signature data_dir:PosixPath/0/?, batch_size:int/0/int, workers:int/0/int · returned DataLoader · level recorded 2026-09-24
infer_suffix repro/iclr24/utils/download_imagenet_from_hf.py ran BSD-3-Clause (permissive) · 5db6a07ebbde4147 · report fixture: signature image_bytes:bytes/0/? · returned str · level recorded 2026-09-24
is_primary_process repro/iclr24/utils/train_imagenet.py ran BSD-3-Clause (permissive) · 914182d62d18d406 · report fixture: signature args:Args/0/?, ngpus_per_node:int/0/int · returned bool · level recorded 2026-09-24
resolve_token repro/iclr24/utils/download_imagenet_from_hf.py ran fingerprinted BSD-3-Clause (permissive) · 8b2b1cd08a25a990 · report fixture: signature token:str/0/str · returned str · level recorded 2026-09-24
stage_imagenet repro/iclr24/utils/imagenet_data.py ran BSD-3-Clause (permissive) · 36a66c7a63a7bb23 · report fixture: signature source_dir:PosixPath/0/?, dest_dir:PosixPath/0/?, mode:str/0/str · returned ImageNetStatus · level recorded 2026-09-24
to_2tuple in 25 papers repro/icml25/utils/pathnorm_transform.py ran fingerprinted BSD-3-Clause (permissive) · 52b674f7653b81f1 · report fixture: signature value:int/0/int · returned tuple · level recorded 2026-09-24
validate_path_norm_support pathnorm.py ran BSD-3-Clause (permissive) · ef4505d66a1f15cd · report fixture: signature model:callable/0/?, input_tensor:Tensor/4/float · returned PathNormSupportReport · level recorded 2026-09-24
build_training_args repro/icml25/utils/finetune_pruned.py unverified BSD-3-Clause (permissive) · dbcf7d222a1bcd97 · report
compute_path_norm pathnorm.py unverified BSD-3-Clause (permissive) · 3d4115d0e8e0f23d · report
compute_path_norms pathnorm.py unverified BSD-3-Clause (permissive) · f2be78276ff88def · report
get_model in 368 papers repro/iclr24/utils/pretrained_resnets.py unverified BSD-3-Clause (permissive) · 03655098d4ec5888 · report
unwrap_model in 41 papers repro/icml25/utils/pathnorm_transform.py unverified BSD-3-Clause (permissive) · 25a99cb17f71ec59 · 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