Construct · 1 fields · 1 citations

decoupled weight decay: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Machine learning

applying weight decay as a separate shrinkage step rather than as an L2 penalty folded into the gradient, which matters for adaptive optimizers such as Adam.

In machine learning, decoupled weight decay refers to applying weight decay as a separate shrinkage step rather than as an L2 penalty folded into the gradient, which matters for adaptive optimizers such as Adam. This meaning comes from Loshchilov (2017) in arXiv.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how decoupled weight decay sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

decay4 fields · 5 citationsjingle · one word, four constructs gradient4 fields · 4 citationsjingle · one word, four constructs learning6 fields · 14 citationsjingle · one name, six constructs

References

Loshchilov, I., & Hutter, F. (2017). Decoupled Weight Decay Regularization. arXiv. https://doi.org/10.48550/arxiv.1711.05101

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct