Methods › General › Normalization › Weight Normalization

Weight Normalization

88 papers tagged archive 2025-07-28

Introduced by Tim Salimans et al. in Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks

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

Weight Normalization is a normalization method for training neural networks. It is inspired by batch normalization, but it is a deterministic method that does not share batch normalization's property of adding noise to the gradients. It reparameterizes each k-dimentional weight vector w in terms of a parameter vector v and a scalar parameter g and to perform stochastic gradient descent with respect to those parameters instead. Weight vectors are expressed in terms of the new parameters using:

w = g/(‖ textbfv‖)v

where v is a k-dimensional vector, g is a scalar, and ‖v‖ denotes the Euclidean norm of v. This reparameterization has the effect of fixing the Euclidean norm of the weight vector w: we now have ‖w‖= g, independent of the parameters v.

PaperSourceSee Code · pytorch/pytorch

Papers archive 2025-07-28

30 shown of 88, 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.

Tasks archive 2025-07-28

20 shown of 101 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
Speech Synthesis12
GPU7
Image Classification7
CPU6
Image Generation6
Quantization6
Text to Speech6
text-to-speech6
Decoder5
image-classification5
General Classification4
BIG-bench Machine Learning3
Machine Translation3
Model Compression3
Representation Learning3
Translation3
Audio Synthesis2
Classification2
Density Estimation2
Domain Adaptation2

Usage over time archive 2025-07-28

Papers per year tagged with Weight Normalization: 2016 to 2025, peak 19 19 0 2016: 4 papers 2016 2017: 7 papers 2017 2018: 5 papers 2018 2019: 14 papers 2019 2020: 19 papers 2020 2021: 13 papers 2021 2022: 9 papers 2022 2023: 5 papers 2023 2024: 10 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (88 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