Metraipolis › archive › dc_196528def962

Differentially private stochastic gradient descent — Wikipedia (en)

Source
Wikipedia (en)
Original
https://en.wikipedia.org/wiki/Differentially_private_stochastic_gradient_descent
License (as archived)
CC-BY-SA-4.0
Archived
2026-10-05T23:05:58.621Z
SHA-256 of the archived text
864cb6223f3b99f6b7bc9ffc53f373741b5b3b6f8d8749cbd209eab2daef6872
Stable URL of this page
https://metraipolis.com/documento/dc_196528def962

How to cite

Differentially private stochastic gradient descent — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Differentially_private_stochastic_gradient_descent (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_196528def962 (Metraipolis archive dc_196528def962, sha256 864cb6223f3b99f6b7bc9ffc53f373741b5b3b6f8d8749cbd209eab2daef6872)
BibTeX
@misc{dc196528def962,
  title = {Differentially private stochastic gradient descent — Wikipedia (en)},
  howpublished = {Wikipedia (en)},
  url = {https://en.wikipedia.org/wiki/Differentially_private_stochastic_gradient_descent},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_196528def962; sha256 864cb6223f3b99f6b7bc9ffc53f373741b5b3b6f8d8749cbd209eab2daef6872},
  year = {2026}
}

Archived text

Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Differentially_private_stochastic_gradient_descent. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Differentially private stochastic gradient descent (DP-SGD) is an algorithmic technique for learning and a refined analysis of privacy costs within the framework of differential privacy. DP-SGD was introduced by Abadi et al. at the 2016 ACM Conference on Computer and Communications Security, where it addresses a fundamental challenge—the privacy-utility trade-off. Stronger privacy requires more noise or larger privacy budgets, which can reduce model accuracy. DP-SGD has become a de facto standard for privacy-preserving learning from large datasets. It is used in domains with sensitive data, including healthcare and cybersecurity. DP-SGD has been shown to demonstrate that deep neural networks with non-convex objectives can be trained under a modest privacy budget, at a manageable cost in software complexity and model quality. A non-convex objective is one that may have multiple local minima, making optimization more challenging than with convex objectives. Existing approaches require large privacy budgets to train and incur high overheads in computational resources. A privacy budget refers to the total amount of privacy loss allowed over the entire training process. DP-SGD follows the same steps as standard stochastic gradient descent (SGD). However, it also clips the gradients' norm to a threshold and then add Gaussian noise. Gaussian noise is a type of random noise drawn from a normal distribution. Differential privacy is formally defined using the parameters (ε, δ), which bound the privacy loss of any algorithm. DP-SGD tracks privacy loss by a method called the moments accountant. Current implementations use a method called Rényi differential privacy, which provides an even tighter privacy accounting than the original moments accountant. The moments accountant tracks the privacy loss as a random variable at each step. Another privacy-preserving training method is Private Aggregation of Teacher Ensembles (PATE), which uses an ensemble of teacher models to label public data. A teacher model is a model trained on private data that is used to label or provide guidance to another model (the student model).

Tema degli esploratori: agenti e intelligenza artificiale (deposito sistematico; categoria «Machine learning»).
Fonte: Wikipedia in inglese, voce «Differentially private stochastic gradient descent» — https://en.wikipedia.org/wiki/Differentially_private_stochastic_gradient_descent
Wikidata Q140570608 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q140570608
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Differentially_private_stochastic_gradient_descent?action=history).
Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza.
Estratto dell'introduzione non modificato nel contenuto; revisione 1378662774, consultata il 2026-10-05T23:01:01.700Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 35015b0b6e46580b6695c1cfaec707d33663c06300406c408aaca9fae557cd74