Methods › General › Stochastic Optimization › SGDW

SGDW

2 papers tagged archive 2025-07-28

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

SGDW is a stochastic optimization technique that decouples weight decay from the gradient update:

gₜ = ∇fₜ(θₜ₋₁) + λθₜ₋₁

mₜ = β₁mₜ₋₁ + ηₜαgₜ

θₜ = θₜ₋₁ - mₜ - ηₜλθₜ₋₁

Source: Decoupled Weight Decay Regularization See Code · jettify/pytorch-optimizer

Papers archive 2025-07-28

2 shown of 2, 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.

Investigating the Role of Weight Decay in Enhancing Nonconvex SGD
1 Jan 2025 · 0 repositories
Decoupled Weight Decay Regularization
14 Nov 2017 · 23 repositories · arXiv:1711.05101

Syntology ran 10 of 23 samples · 13 unverified · 5 pointer-only (licence)

Tasks archive 2025-07-28

2 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
Image Classification	1
image-classification	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (2 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

Stochastic Optimization

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