Construct · 1 fields · 1 citations

sharpness-aware minimization: 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

an optimizer that seeks parameters whose whole neighborhood has low loss, minimizing loss value and sharpness together to improve generalization.

In machine learning, sharpness-aware minimization refers to an optimizer that seeks parameters whose whole neighborhood has low loss, minimizing loss value and sharpness together to improve generalization. This meaning comes from Foret (2020) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how sharpness-aware minimization 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

generalization6 fields · 16 citationsjingle · one name, six constructs learning6 fields · 14 citationsjingle · one name, six constructs loss2 fields · 3 citationsjingle · one word, two constructs

References

Foret, P., Kleiner, A., Mobahi, H., & Neyshabur, B. (2020). Sharpness-Aware Minimization for Efficiently Improving Generalization. arXiv. https://doi.org/10.48550/arxiv.2010.01412

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