Papers › Improving Deep Learning Optimization through Constrained Parameter Regularization

Improving Deep Learning Optimization through Constrained Parameter Regularization

15 Nov 2023arXiv:2311.09058archive 2025-07-28

Jörg K. H. Franke, Michael Hefenbrock, Gregor Koehler, Frank Hutter

Regularization is a critical component in deep learning. The most commonly used approach, weight decay, applies a constant penalty coefficient uniformly across all parameters. This may be overly restrictive for some parameters, while insufficient for others. To address this, we present Constrained Parameter Regularization (CPR) as an alternative to traditional weight decay. Unlike the uniform application of a single penalty, CPR enforces an upper bound on a statistical measure, such as the L2-norm, of individual parameter matrices. Consequently, learning becomes a constraint optimization problem, which we tackle using an adaptation of the augmented Lagrangian method. CPR introduces only a minor runtime overhead and only requires setting an upper bound. We propose simple yet efficient mechanisms for initializing this bound, making CPR rely on no hyperparameter or one, akin to weight decay. Our empirical studies on computer vision and language modeling tasks demonstrate CPR's effectiveness. The results show that CPR can outperform traditional weight decay and increase performance in pre-training and fine-tuning.

PaperPDFCodeCode Syntology ranMethod as code

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 13 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 4 ran (0 with no instrument failure; 4 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 4 samples that ran has no recorded date.

automl/cpr officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 4 ran (4 instrument-failed) · 9 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

13 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

4ran · our draft was wrong
9unverified

Licence: 0 of the 13 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 automl/cpr. “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.

automl/cpr official repository 13 samples, 4 ran (4 instrument-failed) · 9 unverified
_disable_dynamo_if_unsupported pytorch_cpr/adamcpr.py ran · our draft was wrong Apache-2.0 (permissive) · 77e74503b4a6ddf3 · report fixture: signature single_tensor_fn:callable/0/? · returned function · level recorded 2026-09-22
_get_capturable_supported_devices pytorch_cpr/adamcpr.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 8d0c76131beabbb9 · report fixture: signature supports_xla:bool/0/bool · returned list · level recorded 2026-09-22
group_parameters_for_cpr_optimizer pytorch_cpr/adamcpr.py ran · our draft was wrong Apache-2.0 (permissive) · 2f3d97790ecb08b8 · report fixture: signature model:callable/0/?, regularize_embedding:bool/0/bool · returned list · level recorded 2026-09-24
wd_group_named_parameters examples/train_cifar100_task.py ran · our draft was wrong Apache-2.0 (permissive) · 2d82e29243858703 · report fixture: signature model:callable/0/?, weight_decay:float/0/float · returned list · level recorded, date not recorded
AdamCPR pytorch_cpr/adamcpr.py unverified Apache-2.0 (permissive) · 20c73d219b728426 · report
_multi_tensor_adamcpr pytorch_cpr/adamcpr.py unverified Apache-2.0 (permissive) · ee694b63b0bc4895 · report
_single_tensor_adamcpr pytorch_cpr/adamcpr.py unverified Apache-2.0 (permissive) · 3e3e242295adb363 · report
adamcpr pytorch_cpr/adamcpr.py unverified Apache-2.0 (permissive) · a14f930855d7e136 · report
huber_update pytorch_cpr/adamcpr.py unverified Apache-2.0 (permissive) · 5d028ca59f740e80 · report
l1_update pytorch_cpr/adamcpr.py unverified Apache-2.0 (permissive) · f5fe436ea316e71f · report
l2_update pytorch_cpr/adamcpr.py unverified Apache-2.0 (permissive) · 3babf488a0693b0b · report
single_initilize_kappa pytorch_cpr/adamcpr.py unverified Apache-2.0 (permissive) · 08254562e66103c1 · report
std_update pytorch_cpr/adamcpr.py unverified Apache-2.0 (permissive) · ddf970467b201f00 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Constrained Parameter Regularization (CPR) (graph method: Constrained Parameter Regularization (CPR)). 12 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. AdamCPR entry · level 0 · unverified · 20c73d219b728426
  2. adamcpr update_rule · level 0 · unverified · a14f930855d7e136
  3. group_parameters_for_cpr_optimizer helper · level 1 · ran · our draft was wrong · 2f3d97790ecb08b8
  4. single_initilize_kappa helper · level 0 · unverified · 08254562e66103c1
  5. _disable_dynamo_if_unsupported helper · level 1 · ran · our draft was wrong · 77e74503b4a6ddf3
  6. _multi_tensor_adamcpr update_rule · level 0 · unverified · ee694b63b0bc4895
  7. _single_tensor_adamcpr update_rule · level 0 · unverified · 3e3e242295adb363
  8. _get_capturable_supported_devices helper · level 1 · ran · our draft was wrong · 8d0c76131beabbb9
  9. huber_update update_rule · level 0 · unverified · 5d028ca59f740e80
  10. l1_update update_rule · level 0 · unverified · f5fe436ea316e71f
  11. l2_update update_rule · level 0 · unverified · 3babf488a0693b0b
  12. std_update update_rule · level 0 · unverified · ddf970467b201f00

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2311.09058") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Deep LearningImage ClassificationLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Weight Decay

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