Construct · 1 fields · 1 citations

differentially private stochastic gradient descent: a standalone construct

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

● anchor · a standalone construct Nearest construct by meaning·not indexed
differentially privatestochastic gradient descent1 CONSTRUCTDifferentially privateABADI · MACHINE LEARNING

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

Machine learning security

training a network with clipped per-example gradients plus calibrated noise, so the trained model satisfies a formal differential privacy guarantee.

In machine learning security, differentially private stochastic gradient descent refers to training a network with clipped per-example gradients plus calibrated noise, so the trained model satisfies a formal differential privacy guarantee. This meaning comes from Abadi (2016) in Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security.[1]

Unit
Recovery means
Measured by

Next

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

See how differentially private stochastic gradient descent sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in ColliderExport BibTeXReport this entry

Nearby constructs

descent3 fields · 4 citationsjingle · one word, three constructsgradient descent1 fields · 4 citationsanchor · a standalone constructgradient4 fields · 4 citationsjingle · one word, four constructs

References

  1. Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016). Deep Learning with Differential Privacy. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. https://doi.org/10.1145/2976749.2978318

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