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...

Descripció completa

Dades bibliogràfiques

Autors principals:	Sifan Deng, Kai Zhang, Weilin Zhang, Huiqin Jiang, Pei-Wei Tsai
Format:	Artigo
Idioma:	Inglês
Publicat:	Nature Portfolio 2026-03-01
Col·lecció:	Scientific Reports
Matèries:	Differential privacy Deep learning Buffered rejection mechanism
Accés en línia:	https://doi.org/10.1038/s41598-026-44009-2
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!