Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics

• Published in: arXiv.org
• Main Authors: Wu, Xi, Li, Fengan, Kumar, Arun, Chaudhuri, Kamalika, Jha, Somesh, Naughton, Jeffrey F
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 23.03.2017
• Subjects: Algorithms; Bolts; Mathematical analysis; Model accuracy; Privacy; Sensitivity analysis

While significant progress has been made separately on analytics systems for scalable stochastic gradient descent (SGD) and private SGD, none of the major scalable analytics frameworks have incorporated differentially private SGD. There are two inter-related issues for this disconnect between resear...