Local Differential Privacy in Decentralized Optimization
arXiv:1902.06101
Abstract
Privacy concerns with sensitive data are receiving increasing attention. In this paper, we study local differential privacy (LDP) in interactive decentralized optimization. By constructing random local aggregators, we propose a framework to amplify LDP by a constant. We take Alternating Direction Method of Multipliers (ADMM), and decentralized gradient descent as two concrete examples, where experiments support our theory. In an asymptotic view, we address the following question: Under LDP, is it possible to design a distributed private minimizer for arbitrary closed convex constraints with utility loss not explicitly dependent on dimensionality? As an affiliated result, we also show that with merely linear secret sharing, information theoretic privacy is achievable for bounded colluding agents.
References in corpus (13)
- Deep Learning with Differential Privacy
- Federated Learning: Strategies for Improving Communication Efficiency
- On the Linear Convergence of the ADMM in Decentralized Consensus Optimization
- Multi-Agent Distributed Optimization via Inexact Consensus ADMM
- Differentially Private Distributed Constrained Optimization
- Extremal Mechanisms for Local Differential Privacy
- Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12
- Privacy Amplification by Iteration
- Differentially Private Bayesian Learning on Distributed Data
- Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM
- Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry
- Noninteractive Locally Private Learning of Linear Models via Polynomial Approximations
- Recycled ADMM: Improve Privacy and Accuracy with Less Computation in Distributed Algorithms