Methods › General › Regularization › SVD Parameterization
Singular Value Decomposition Parameterization
SVD Parameterization
Introduced by Jiong Zhang et al. in Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The archive carries no description for this method.
Papers archive 2025-07-28
5 shown of 5, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
The Condition Number as a Scale-Invariant Proxy for Information Encoding in Neural Units 19 Jun 2025 · 1 repository
-
An Introduction to Matrix factorization and Factorization Machines in Recommendation System, and Beyond 12 Mar 2022 · 0 repositories · arXiv:2203.11026
-
Spectral Tensor Train Parameterization of Deep Learning Layers 7 Mar 2021 · 1 repository · arXiv:2103.04217
-
Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization 25 Mar 2018 · 1 repository · arXiv:1803.09327
-
Recommender Systems 6 Feb 2012 · 1 repository · arXiv:1202.1112
Tasks archive 2025-07-28
8 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Recommendation Systems | 2 |
| Deep Learning | 1 |
| Image Classification | 1 |
| Image Generation | 1 |
| Large Language Model | 1 |
| Multimodal Large Language Model | 1 |
| Neural Network Compression | 1 |
| image-classification | 1 |
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