The Relative Gaussian Mechanism and its Application to Private Gradient Descent

Abstract

The Gaussian Mechanism (GM), which consists in adding Gaussian noise to a vector-valued query before releasing it, is a standard privacy protection mechanism. In particular, given that the query respects some L2 sensitivity property (the L2 distance between outputs on any two neighboring inputs is bounded), GM guarantees Rényi Differential Privacy (RDP). Unfortunately, precisely bounding the L2 sensitivity can be hard, thus leading to loose privacy bounds. In this work, we consider a Relative L2 sensitivity assumption, in which the bound on the distance between two query outputs may also depend on their norm. Leveraging this assumption, we introduce the Relative Gaussian Mechanism (RGM), in which the variance of the noise depends on the norm of the output. We prove tight bounds on the RDP parameters under relative L2 sensitivity, and characterize the privacy loss incurred by using output-dependent noise. In particular, we show that RGM naturally adapts to a latent variable that would control the norm of the output. Finally, we instantiate our framework to show tight guarantees for Private Gradient Descent, a problem that naturally fits our relative L2 sensitivity assumption.

References in corpus (9)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Deep Learning with Differential Privacy
• Private Stochastic Convex Optimization with Optimal Rates
• AdaCliP: Adaptive Clipping for Private SGD
• Understanding Gradient Clipping in Private SGD: A Geometric Perspective
• Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation
• Propose, Test, Release: Differentially private estimation with high probability
• Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization
• Private optimization in the interpolation regime: faster rates and hardness results