Methods › General › Normalization › Spectral Normalization

Spectral Normalization

220 papers tagged archive 2025-07-28

Introduced by Takeru Miyato et al. in Spectral Normalization for Generative Adversarial Networks

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Spectral Normalization is a normalization technique used for generative adversarial networks, used to stabilize training of the discriminator. Spectral normalization has the convenient property that the Lipschitz constant is the only hyper-parameter to be tuned.

It controls the Lipschitz constant of the discriminator f by constraining the spectral norm of each layer g : hᵢₙ →hₒᵤₜ. The Lipschitz norm ‖g‖_(Lip) is equal to supₕσ(∇g(h)), where σ(a) is the spectral norm of the matrix A (L₂ matrix norm of A):

σ(a) = max_(h:h≠0)(‖Ah‖₂)/(‖h‖₂) = max_(‖h‖₂≤1)‖Ah‖₂

which is equivalent to the largest singular value of A. Therefore for a linear layer g(h) = Wh the norm is given by ‖g‖_(Lip) = supₕσ(∇g(h)) = supₕσ(W) = σ(W). Spectral normalization normalizes the spectral norm of the weight matrix W so it satisfies the Lipschitz constraint σ(W) = 1:

W̅_(SN)(W) = W / σ(W)

PaperSourceSee Code · christiancosgrove/pytorch-spectral-normalization-gan

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 39 in the graph, strongest link: official). This answer is about arXiv:1802.05957, the paper the archive credits with this method.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:1802.05957 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 25 ran (of which 9 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified (of 31 harvested samples) · 15 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

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: 220 · with a code link: 115 · where Syntology ran a sample: 36 (30 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (36 of 220 tagged: 30 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)

Page 1 of 3: papers 1 to 100 of 220, 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.

Tasks archive 2025-07-28

20 shown of 201 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Generation57
Conditional Image Generation20
Generative Adversarial Network19
reinforcement-learning17
Reinforcement Learning13
Translation13
Reinforcement Learning (RL)12
Image-to-Image Translation11
Data Augmentation10
Multi-agent Reinforcement Learning9
Super-Resolution9
Image Classification7
Transfer Learning7
Unconditional Image Generation7
Vocal Bursts Intensity Prediction7
image-classification7
Attribute6
Deep Reinforcement Learning6
Decision Making5
Denoising5

Usage over time archive 2025-07-28

Papers per year tagged with Spectral Normalization: 2018 to 2025, peak 48 48 0 2018: 14 papers 2018 2019: 22 papers 2019 2020: 48 papers 2020 2021: 37 papers 2021 2022: 41 papers 2022 2023: 43 papers 2023 2024: 12 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (220 dated). Bars are counts, not a trend claim.

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

Normalization

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