Methods › General › Normalization › Gradient Normalization
Gradient Normalization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Gradient Normalization is a normalization method for Generative Adversarial Networks to tackle the training instability of generative adversarial networks caused by the sharp gradient space. Unlike existing work such as gradient penalty and spectral normalization, the proposed GN only imposes a hard 1-Lipschitz constraint on the discriminator function, which increases the capacity of the network.
In Syntology repository known, no verified implementation (declared_code; repositories: 2 listed of 2 in the graph, strongest link: official). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2109.02235) is about this method is not checked.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- Gradient Cuff · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Gradient Cuff') - Gradient Surgery · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Gradient Surgery') - phantom gradient · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='phantom gradient') - Gradient Flossing · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Gradient Flossing') - Gradient Sign Dropout · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Gradient Sign Dropout') - Gradient Magnification · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Gradient Magnification')
Origin paper of this answer, arXiv:2109.02235 (its page on this site · its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 15 · with a code link: 7 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 15 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 15 of 15, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
AlphaGrad: Non-Linear Gradient Normalization Optimizer 22 Apr 2025 · 0 repositories · arXiv:2504.16020
-
Stable-SPAM: How to Train in 4-Bit More Stably than 16-Bit Adam 24 Feb 2025 · 1 repository · arXiv:2502.17055
-
Network scaling and scale-driven loss balancing for intelligent poroelastography 27 Oct 2024 · 0 repositories · arXiv:2411.08886
-
Gradient Normalization Provably Benefits Nonconvex SGD under Heavy-Tailed Noise 21 Oct 2024 · 0 repositories · arXiv:2410.16561
-
Adaptive Gradient Normalization and Independent Sampling for (Stochastic) Generalized-Smooth Optimization 17 Oct 2024 · 0 repositories · arXiv:2410.14054
-
Training on Fake Labels: Mitigating Label Leakage in Split Learning via Secure Dimension Transformation 11 Oct 2024 · 0 repositories · arXiv:2410.09125
-
Adaptive Gradient Regularization: A Faster and Generalizable Optimization Technique for Deep Neural Networks 24 Jul 2024 · 0 repositories · arXiv:2407.16944
-
OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes 23 Aug 2023 · 1 repository · arXiv:2308.11928Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Continual Domain Adaptation on Aerial Images under Gradually Degrading Weather 2 Aug 2023 · 1 repository · arXiv:2308.00924
-
Penalty Gradient Normalization for Generative Adversarial Networks 23 Jun 2023 · 1 repository · arXiv:2306.13576
-
Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima 16 Jun 2023 · 0 repositories · arXiv:2306.09850
-
A Deep Learning Approach Using Masked Image Modeling for Reconstruction of Undersampled K-spaces 24 Aug 2022 · 1 repository · arXiv:2208.11472
-
GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks 4 Nov 2021 · 0 repositories · arXiv:2111.03162
-
Perturbated Gradients Updating within Unit Space for Deep Learning 1 Oct 2021 · 1 repository · arXiv:2110.00199
-
Gradient Normalization for Generative Adversarial Networks 6 Sep 2021 · 1 repository · arXiv:2109.02235
Tasks archive 2025-07-28
14 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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