Construct · 1 fields · 1 citations

large-batch generalization gap: 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

networks trained with very large minibatches generalize worse, attributed to their convergence toward sharp minima of the training loss.

In machine learning, large-batch generalization gap refers to networks trained with very large minibatches generalize worse, attributed to their convergence toward sharp minima of the training loss. This meaning comes from Keskar (2016) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how large-batch generalization gap 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

convergence4 fields · 4 citationsjingle · one word, four constructs generalization6 fields · 16 citationsjingle · one name, six constructs learning6 fields · 14 citationsjingle · one name, six constructs

References

Keskar, N. S., Mudigere, D., Nocedal, J., Smelyanskiy, M., & Tang, P. T. P. (2016). On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. arXiv. https://doi.org/10.48550/arxiv.1609.04836

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