Construct · 1 fields · 1 citations

stochastic weight averaging: 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

averaging the weights visited by stochastic gradient descent under a cyclical or high learning rate, which finds wider optima that generalize better.

In machine learning, stochastic weight averaging refers to averaging the weights visited by stochastic gradient descent under a cyclical or high learning rate, which finds wider optima that generalize better. This meaning comes from Izmailov (2018) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how stochastic weight averaging 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

descent3 fields · 4 citationsjingle · one word, three constructs gradient descent1 fields · 4 citationsanchor · a standalone construct gradient4 fields · 4 citationsjingle · one word, four constructs

References

Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., & Wilson, A. G. (2018). Averaging Weights Leads to Wider Optima and Better Generalization. arXiv. https://doi.org/10.48550/arxiv.1803.05407

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