Methods › General › Regularization › Off-Diagonal Orthogonal Regularization

Off-Diagonal Orthogonal Regularization

132 papers tagged archive 2025-07-28

Introduced by Andrew Brock et al. in Large Scale GAN Training for High Fidelity Natural Image Synthesis

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

Off-Diagonal Orthogonal Regularization is a modified form of orthogonal regularization originally used in BigGAN. The original orthogonal regularization is known to be limiting so the authors explore several variants designed to relax the constraint while still imparting the desired smoothness to the models. They opt for a modification where they remove diagonal terms from the regularization, and aim to minimize the pairwise cosine similarity between filters but does not constrain their norm:

Rᵦ(W) = β|| WᵀW ⊙(1-I) ||²_F

where 1 denotes a matrix with all elements set to 1. The authors sweep β values and select 10⁻⁴.

PaperSourceSee Code · ajbrock/BigGAN-PyTorch

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Orthogonality Regularization; regularization-sharpness tradeoff; Offline Variance Regularization (OVR); Orthogonal Jacobian Regularization (OroJaR); off-policy log-dispersion regularization (LDR); Orthogonal Decoupling Contrastive Regularization (ODCR); Off-log metric; Off-policy DAE.

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.

Papers archive 2025-07-28

archive papers tagged: 132 · with a code link: 70 · where Syntology ran a sample: 24 (20 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (24 of 132 tagged: 20 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 132, 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 141 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 Generation37
Conditional Image Generation15
Generative Adversarial Network11
reinforcement-learning9
Multi-agent Reinforcement Learning7
Reinforcement Learning7
Data Augmentation6
Reinforcement Learning (RL)6
Super-Resolution6
Vocal Bursts Intensity Prediction6
Decision Making5
Unconditional Image Generation5
Attribute4
Clustering4
Denoising4
Diversity4
Object4
Transfer Learning4
Benchmarking3
Decoder3

Usage over time archive 2025-07-28

Papers per year tagged with Off-Diagonal Orthogonal Regularization: 2018 to 2024, peak 37 37 0 2018: 2 papers 2018 2019: 10 papers 2019 2020: 28 papers 2020 2021: 20 papers 2021 2022: 33 papers 2022 2023: 37 papers 2023 2024: 2 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (132 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

Regularization

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