Differentially Private Distributed Convex Optimization via Functional Perturbation

TL;DR

This paper introduces a novel approach for differentially private distributed convex optimization by perturbing individual functions with Laplace noise, overcoming limitations of message perturbation methods, and providing bounds on privacy-accuracy trade-offs.

Contribution

The paper proposes a functional perturbation framework for differential privacy in distributed optimization, including smoothing techniques and bounds on optimizer accuracy.

Findings

Functional perturbation achieves privacy without destabilizing dynamics.

Post-processing restores convexity and smoothness of perturbed functions.

Explicit bounds on the privacy-accuracy trade-off are derived.

Abstract

We study a class of distributed convex constrained optimization problems where a group of agents aim to minimize the sum of individual objective functions while each desires that any information about its objective function is kept private. We prove the impossibility of achieving differential privacy using strategies based on perturbing the inter-agent messages with noise when the underlying noise-free dynamics are asymptotically stable. This justifies our algorithmic solution based on the perturbation of individual functions with Laplace noise. To this end, we establish a general framework for differentially private handling of functional data. We further design post-processing steps that ensure the perturbed functions regain the smoothness and convexity properties of the original functions while preserving the differentially private guarantees of the functional perturbation step. This methodology allows us to use any distributed coordination algorithm to solve the optimization problem on the noisy functions. Finally, we explicitly bound the magnitude of the expected distance between the perturbed and true optimizers which leads to an upper bound on the privacy-accuracy trade-off curve. Simulations illustrate our results.