High-Dimensional Asymptotics of Differentially Private PCA

arXiv:2511.07270v2 Announce Type: replace-cross Abstract: In differential privacy, statistics of a sensitive dataset are privatized by introducing random noise. Most privacy analyses provide privacy bounds specifying a noise level sufficient to achieve a target privacy guarant...

🔗 Read more: https://arxiv.org/abs/2511.07270

#News #Tech #Security #Math #Policy #Academic