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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2310.01225")

Code

Syntology Ran 15 of 20 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 15 ran with no contract checked.

By repository: official repository: 20 samples from 1 repository, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

agonon/pathnorm_toolkit officialmentioned in papermentioned on GitHubpytorchBSD-3-Clause 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; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, 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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

adaptive_pool_params agonon/pathnorm_toolkit/repro/icml25/utils/pathnorm_transform.py official repository ran fingerprinted BSD-3-Clause (permissive) · d504804f0f9ac808 · report
check_imagenet_prepared agonon/pathnorm_toolkit/repro/iclr24/utils/imagenet_data.py official repository ran BSD-3-Clause (permissive) · 4af14115cc3aee7e · report
class_dir_name agonon/pathnorm_toolkit/repro/iclr24/utils/download_imagenet_from_hf.py official repository ran fingerprinted BSD-3-Clause (permissive) · 6e545c1bdc3f7cec · report
count_files_recursive agonon/pathnorm_toolkit/repro/iclr24/utils/imagenet_data.py official repository ran BSD-3-Clause (permissive) · 6bbf2dc539716669 · report
estimate_total_epoch_steps agonon/pathnorm_toolkit/repro/iclr24/utils/train_imagenet.py official repository ran BSD-3-Clause (permissive) · 3e27e0086ed49361 · report
format_duration agonon/pathnorm_toolkit/repro/iclr24/utils/train_imagenet.py official repository ran fingerprinted BSD-3-Clause (permissive) · 108ebe73d0b32ec2 · report
get_imagenet_train_val_test agonon/pathnorm_toolkit/repro/iclr24/utils/imagenet_dataset.py official repository ran BSD-3-Clause (permissive) · cfe74f26307fd802 · report
get_imagenet_transforms agonon/pathnorm_toolkit/repro/iclr24/utils/imagenet_dataset.py official repository ran BSD-3-Clause (permissive) · b417f83635432b4d · report
get_trainloader agonon/pathnorm_toolkit/repro/iclr24/utils/pretrained_resnets.py official repository ran BSD-3-Clause (permissive) · 15c4080169910373 · report
infer_suffix agonon/pathnorm_toolkit/repro/iclr24/utils/download_imagenet_from_hf.py official repository ran BSD-3-Clause (permissive) · 5db6a07ebbde4147 · report
is_primary_process agonon/pathnorm_toolkit/repro/iclr24/utils/train_imagenet.py official repository ran BSD-3-Clause (permissive) · 914182d62d18d406 · report
resolve_token agonon/pathnorm_toolkit/repro/iclr24/utils/download_imagenet_from_hf.py official repository ran fingerprinted BSD-3-Clause (permissive) · 8b2b1cd08a25a990 · report
stage_imagenet agonon/pathnorm_toolkit/repro/iclr24/utils/imagenet_data.py official repository ran BSD-3-Clause (permissive) · 36a66c7a63a7bb23 · report
to_2tuple agonon/pathnorm_toolkit/repro/icml25/utils/pathnorm_transform.py official repository ran fingerprinted BSD-3-Clause (permissive) · 52b674f7653b81f1 · report
validate_path_norm_support agonon/pathnorm_toolkit/pathnorm.py official repository ran BSD-3-Clause (permissive) · ef4505d66a1f15cd · report
build_training_args agonon/pathnorm_toolkit/repro/icml25/utils/finetune_pruned.py official repository unverified BSD-3-Clause (permissive) · dbcf7d222a1bcd97 · report
compute_path_norm agonon/pathnorm_toolkit/pathnorm.py official repository unverified BSD-3-Clause (permissive) · 3d4115d0e8e0f23d · report
compute_path_norms agonon/pathnorm_toolkit/pathnorm.py official repository unverified BSD-3-Clause (permissive) · f2be78276ff88def · report
get_model agonon/pathnorm_toolkit/repro/iclr24/utils/pretrained_resnets.py official repository unverified BSD-3-Clause (permissive) · 03655098d4ec5888 · report
unwrap_model agonon/pathnorm_toolkit/repro/icml25/utils/pathnorm_transform.py official repository 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