Not all noise is accounted equally: How differentially private learning benefits from large sampling rates

12 October 2021

Papers citing "Not all noise is accounted equally: How differentially private learning benefits from large sampling rates"

3 / 3 papers shown

Title
Individual Privacy Accounting via a Renyi Filter Vitaly Feldman Tijana Zrnic 36 77 0 25 Aug 2020
Tempered Sigmoid Activations for Deep Learning with Differential Privacy Nicolas Papernot Abhradeep Thakurta Shuang Song Steve Chien Ulfar Erlingsson AAML 104 155 0 28 Jul 2020
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 251 2,696 0 15 Sep 2016