Stabilizing updates in differentially private stochastic gradient descent with buffered rejection

Abstract Differentially private stochastic gradient descent is a standard algorithm for training deep models on sensitive data, but under tight privacy budgets it must add large noise to every step, which slows convergence and reduces accuracy. Selective update methods for differential private stoch...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Sifan Deng, Kai Zhang, Weilin Zhang, Huiqin Jiang, Pei-Wei Tsai
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Nature Portfolio 2026-03-01
Edice:	Scientific Reports
Témata:	Differential privacy Deep learning Buffered rejection mechanism
On-line přístup:	https://doi.org/10.1038/s41598-026-44009-2
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!